xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-14 06:25:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

enable all

Browse Source 
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
This commit is contained in:
Zhuohan Li 2025-10-15 17:01:03 -07:00
parent 1f4472ba5f
commit 98e71a4954
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/model_executor/layers/moe/grouped_gemm_no_abstraction.py
View File

@ -351,6 +351,6 @@ def run_triton_group_gemm_masked_bf16(
# run_batched_deepgemm_masked_fp8(512, 8, 1024, 512) # run_batched_deepgemm_masked_fp8(512, 8, 1024, 512)
run_batched_deepgemm_contiguous_bf16(512, 8, 1024, 512) run_batched_deepgemm_contiguous_bf16(512, 8, 1024, 512)
# run_batched_deepgemm_masked_bf16(512, 8, 1024, 512) run_batched_deepgemm_masked_bf16(512, 8, 1024, 512)
# run_triton_group_gemm_contiguous_bf16(512, 8, 1024, 512, 4) run_triton_group_gemm_contiguous_bf16(512, 8, 1024, 512, 4)
# run_triton_group_gemm_masked_bf16(512, 8, 1024, 512) run_triton_group_gemm_masked_bf16(512, 8, 1024, 512)