mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-04-08 02:17:04 +08:00
c6c9122d50
Signed-off-by: Faqin Zhong <faqin.zhong@gmail.com> Co-authored-by: Duncan Moss <djm.moss@gmail.com>
24 lines
961 B
Plaintext
24 lines
961 B
Plaintext
#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
|