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

[ROCm][CI] Fix AITER test flakiness by using explicit attention backend (#32346)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
This commit is contained in:
Andreas Karatzas
2026-01-21 23:55:25 -06:00
committed by GitHub
parent 019e2c3b7c
commit eb1629da24
3 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json
View File

@@ -45,14 +45,14 @@
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
"kpack": 1
},
"24": {
"BLOCK_SIZE_M": 16,