vllm/vllm/model_executor/layers/quantization/utils/configs at fd0e3772441a32e1c5948d62a8702417fac59979 - vllm

N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1024,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD][QWEN3-NEXT] FP8 Tunings (#32042 )

2026-01-27 09:34:13 +00:00

N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2048,K=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD][QWEN3-NEXT] FP8 Tunings (#32042 )

2026-01-27 09:34:13 +00:00

N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

Tuned H100/H200 triton fp8 block configs for fused_qkv_a_proj (#23939 )

2025-08-29 10:28:35 -07:00

N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

Tuned H100/H200 triton fp8 block configs for fused_qkv_a_proj (#23939 )

2025-08-29 10:28:35 -07:00

N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=5120,K=8192,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json

[Model][Qwen3VL] Tune Triton w8a8 block fp8 kernel for L40s (#29217 )

2025-11-21 17:30:55 -08:00

N=5120,K=25600,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json

[Model][Qwen3VL] Tune Triton w8a8 block fp8 kernel for L40s (#29217 )

2025-11-21 17:30:55 -08:00

N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc][Easy] Remove the space from the file name

2025-02-05 19:23:35 -08:00

N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=9216,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD][QWEN3-NEXT] FP8 Tunings (#32042 )

2026-01-27 09:34:13 +00:00

N=10240,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json

[Model][Qwen3VL] Tune Triton w8a8 block fp8 kernel for L40s (#29217 )

2025-11-21 17:30:55 -08:00

N=12288,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD][QWEN3-NEXT] FP8 Tunings (#32042 )

2026-01-27 09:34:13 +00:00

N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json

[MISC] Check space in the file names in the pre commit checks (#12804 )

2025-02-06 15:36:21 -08:00

N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json

[Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322 )

2025-03-23 01:10:10 -07:00

N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json

[Kernel] Add more tuned configs (#14877 )

2025-03-15 20:25:03 -07:00

N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json

[AMD] [Model] DeepSeek tunings (#13199 )

2025-02-15 03:58:09 -08:00

N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json

MI325 configs, fused_moe_kernel bugfix (#14987 )

2025-03-18 08:05:18 -07:00

N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json

[Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748 )

2025-08-28 11:12:53 +08:00

N=51200,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json

[Model][Qwen3VL] Tune Triton w8a8 block fp8 kernel for L40s (#29217 )

2025-11-21 17:30:55 -08:00

README.md

[Perf] Add Triton config for DeepSeek V3 FP8 EP32 H200 (#23504 )

2025-08-24 18:06:35 -07:00

README.md

Quantization Kernel Config