xiezhongtao
2bd9bd4cc2
将分散在各文件中的CUDA/HIP/MUSA硬件相关头文件引用统一到vendors目录下的对应头文件中，提高代码可维护性。移除重复的头文件引用，优化构建配置。
57 lines
2.9 KiB
C++
57 lines
2.9 KiB
C++
#pragma once
|
|
|
|
#include "../../../../vendors/functions.h"
|
|
|
|
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);
|
|
|
|
void cutlass_scaled_mm_sm90_int8(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);
|
|
|
|
void cutlass_scaled_mm_azp_sm90_int8(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);
|
|
|
|
void cutlass_scaled_mm_blockwise_sm90_fp8(torch::Tensor& out,
|
|
torch::Tensor const& a,
|
|
torch::Tensor const& b,
|
|
torch::Tensor const& a_scales,
|
|
torch::Tensor const& b_scales);
|
|
|
|
void cutlass_scaled_mm_sm100_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);
|
|
|
|
void cutlass_scaled_mm_sm120_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);
|
|
|
|
void cutlass_scaled_mm_blockwise_sm100_fp8(torch::Tensor& out,
|
|
torch::Tensor const& a,
|
|
torch::Tensor const& b,
|
|
torch::Tensor const& a_scales,
|
|
torch::Tensor const& b_scales);
|
|
|
|
void cutlass_scaled_mm_blockwise_sm120_fp8(torch::Tensor& out,
|
|
torch::Tensor const& a,
|
|
torch::Tensor const& b,
|
|
torch::Tensor const& a_scales,
|
|
torch::Tensor const& b_scales);
|
|
} // namespace vllm
|