EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[NVIDIA] [2/N] Optimize silu_and_mul_scaled_fp4_grouped_quant perf (#9556)

Browse Source
This commit is contained in:
Kaixi Hou
2025-08-29 17:17:03 -07:00
committed by GitHub
parent ff9b561817
commit 5c34b4f1c7
7 changed files with 297 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
sgl-kernel/csrc/common_extension.cc
View File

@@ -159,8 +159,7 @@ TORCH_LIBRARY_FRAGMENT(sgl_kernel, m) {
m.def(
"silu_and_mul_scaled_fp4_experts_quant(Tensor! output, Tensor! output_scale,"
"Tensor input, Tensor input_global_scale, Tensor input_offset_by_experts,"
"Tensor output_scale_offset_by_experts, Tensor mask) -> ()");
"Tensor input, Tensor input_global_scale, Tensor mask, bool use_silu_and_mul) -> ()");
m.impl("silu_and_mul_scaled_fp4_experts_quant", torch::kCUDA, &silu_and_mul_scaled_fp4_experts_quant);
m.def(