xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-03 03:50:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

add missing arg

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm 2025-11-03 07:09:52 +00:00
parent b13c4bb25c
commit 7794009661
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/layers/quantization/kernels/scaled_mm/flash_infer.py
View File

@ -22,6 +22,7 @@ def flashinfer_w8a8_scaled_mm(
As: torch.Tensor, As: torch.Tensor,
Bs: torch.Tensor, Bs: torch.Tensor,
bias: torch.Tensor, bias: torch.Tensor,
output_shape: list,
) -> torch.Tensor: ) -> torch.Tensor:
return flashinfer_scaled_fp8_mm( return flashinfer_scaled_fp8_mm(
A, B, out_dtype=out_dtype, scale_a=As, scale_b=Bs, bias=bias A, B, out_dtype=out_dtype, scale_a=As, scale_b=Bs, bias=bias