biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

MI325 configs, fused_moe_kernel bugfix (#14987)

Browse Source 
Signed-off-by: Eugene Kuznetsov <eugene.kuznetsov@amd.com>
This commit is contained in:
ekuznetsov139
2025-03-18 08:05:18 -07:00
committed by GitHub
parent af35d3a3cc
commit 8b793f7ec6
54 changed files with 8878 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

200
vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,200 @@
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 16,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}

200
vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,200 @@
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 16,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}

200
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,200 @@
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"24": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}

200
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,200 @@
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"24": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}

200
vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,200 @@
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"24": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}

7
vllm/model_executor/layers/fused_moe/fused_moe.py
View File

@@ -783,8 +783,12 @@ def invoke_fused_moe_kernel(A: torch.Tensor,
use_int8_w8a16=use_int8_w8a16,
**config,
)
else:
config = config.copy()
BLOCK_SIZE_K = config.pop("BLOCK_SIZE_K")
if block_shape is not None:
BLOCK_SIZE_K = min(BLOCK_SIZE_K, min(block_shape[0],
block_shape[1]))
fused_moe_kernel[grid](
A,
B,
@@ -823,6 +827,7 @@ def invoke_fused_moe_kernel(A: torch.Tensor,
compute_type=compute_type,
use_fp8_w8a8=use_fp8_w8a8,
use_int8_w8a16=use_int8_w8a16,
BLOCK_SIZE_K=BLOCK_SIZE_K,
**config,
)

164
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}

164
vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json Normal file
View File

@@ -0,0 +1,164 @@
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}