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/torch_bindings.cpp
View File

@@ -115,8 +115,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
"silu_and_mul_quant(Tensor! result, Tensor input, Tensor scale) -> ()");
ops.impl("silu_and_mul_quant", torch::kCUDA, &silu_and_mul_quant);
#if (defined(ENABLE_NVFP4_SM100) && ENABLE_NVFP4_SM100) || \
(defined(ENABLE_NVFP4_SM120) && ENABLE_NVFP4_SM120)
#ifndef USE_ROCM
ops.def(
"silu_and_mul_nvfp4_quant(Tensor! result, Tensor! result_block_scale, "
"Tensor input, Tensor input_global_scale) -> ()");