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

[Bugfix][Misc] Fix silu_and_mul_nvfp4_quant issue and extract common utils for nvfp4 kernel source files (#23727)

Browse Source 
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
elvischenv
2025-09-05 05:25:45 +08:00
committed by GitHub
parent 60b755cbcb
commit adc3ddb430
11 changed files with 382 additions and 718 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/ops.h
View File

@@ -130,8 +130,7 @@ void silu_and_mul(torch::Tensor& out, torch::Tensor& input);
void silu_and_mul_quant(torch::Tensor& out, torch::Tensor& input,
torch::Tensor& scale);
#if (defined(ENABLE_NVFP4_SM100) && ENABLE_NVFP4_SM100) || \
(defined(ENABLE_NVFP4_SM120) && ENABLE_NVFP4_SM120)
#ifndef USE_ROCM
void silu_and_mul_nvfp4_quant(torch::Tensor& out,
torch::Tensor& output_block_scale,
torch::Tensor& input,