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

36
csrc/quantization/w8a8/cutlass/scaled_mm_c3x_sm90.cu Normal file
View File

@@ -0,0 +1,36 @@
#include "c3x/scaled_mm_helper.hpp"
#include "c3x/scaled_mm_kernels.hpp"
/*
This file defines quantized GEMM operations using the CUTLASS 3.x API, for
NVIDIA GPUs with sm90a (Hopper).
*/
#if defined ENABLE_SCALED_MM_SM90 && ENABLE_SCALED_MM_SM90
void cutlass_scaled_mm_sm90(torch::Tensor& c, torch::Tensor const& a,
torch::Tensor const& b,
torch::Tensor const& a_scales,
torch::Tensor const& b_scales,
std::optional<torch::Tensor> const& bias) {
dispatch_scaled_mm(c, a, b, a_scales, b_scales, bias,
vllm::cutlass_scaled_mm_sm90_fp8,
vllm::cutlass_scaled_mm_sm90_int8,
vllm::cutlass_scaled_mm_blockwise_sm90_fp8);
}
void cutlass_scaled_mm_azp_sm90(torch::Tensor& out, torch::Tensor const& a,
torch::Tensor const& b,
torch::Tensor const& a_scales,
torch::Tensor const& b_scales,
torch::Tensor const& azp_adj,
std::optional<torch::Tensor> const& azp,
std::optional<torch::Tensor> const& bias) {
TORCH_CHECK(a_scales.dtype() == torch::kFloat32);
TORCH_CHECK(b_scales.dtype() == torch::kFloat32);
vllm::cutlass_scaled_mm_azp_sm90_int8(out, a, b, a_scales, b_scales, azp_adj,
azp, bias);
}
#endif