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

update directory for cutlass w8a8

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
yewentao256
2025-08-27 21:05:41 +00:00
parent c643e63f98
commit 57f2f26a05
42 changed files with 22 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_fp8.cu Normal file
View File

@@ -0,0 +1,23 @@
#include "scaled_mm_kernels.hpp"
#include "scaled_mm_sm90_fp8_dispatch.cuh"
namespace vllm {
void cutlass_scaled_mm_sm90_fp8(torch::Tensor& out, torch::Tensor const& a,
torch::Tensor const& b,
torch::Tensor const& a_scales,
torch::Tensor const& b_scales,
std::optional<torch::Tensor> const& bias) {
TORCH_CHECK(a_scales.is_contiguous() && b_scales.is_contiguous());
if (bias) {
TORCH_CHECK(bias->dtype() == out.dtype(),
"currently bias dtype must match output dtype ", out.dtype());
return cutlass_scaled_mm_sm90_fp8_epilogue<true>(out, a, b, a_scales,
b_scales, *bias);
} else {
return cutlass_scaled_mm_sm90_fp8_epilogue<false>(out, a, b, a_scales,
b_scales);
}
}
} // namespace vllm