File size: 8,585 Bytes
b4cad21 0da5bf5 b4cad21 0da5bf5 b4cad21 0da5bf5 b4cad21 0da5bf5 b4cad21 0da5bf5 b4cad21 0da5bf5 b4cad21 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 |
#include <stddef.h>
#include <torch/all.h>
#include "cutlass/cutlass.h"
#include "scaled_mm_c2x.cuh"
#include "scaled_mm_c2x_sm75_dispatch.cuh"
#include "scaled_mm_c2x_sm80_dispatch.cuh"
#include "scaled_mm_c2x_sm89_fp8_dispatch.cuh"
#include "scaled_mm_c2x_sm89_int8_dispatch.cuh"
#include "cutlass_extensions/epilogue/scaled_mm_epilogues_c2x.hpp"
using namespace vllm;
/*
This file defines quantized GEMM operations using the CUTLASS 2.x API, for
NVIDIA GPUs with SM versions prior to sm90 (Hopper).
*/
template <template <typename, typename> typename Epilogue,
typename... EpilogueArgs>
void cutlass_scaled_mm_sm75_epilogue(torch::Tensor& out, torch::Tensor const& a,
torch::Tensor const& b,
EpilogueArgs&&... epilogue_args) {
TORCH_CHECK(a.dtype() == torch::kInt8);
TORCH_CHECK(b.dtype() == torch::kInt8);
if (out.dtype() == torch::kBFloat16) {
return cutlass_gemm_sm75_dispatch<int8_t, cutlass::bfloat16_t, Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
} else {
TORCH_CHECK(out.dtype() == torch::kFloat16);
return cutlass_gemm_sm75_dispatch<int8_t, cutlass::half_t, Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
}
}
void cutlass_scaled_mm_sm75(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.dtype() == torch::kFloat32);
TORCH_CHECK(b_scales.dtype() == torch::kFloat32);
if (bias) {
TORCH_CHECK(bias->dtype() == out.dtype(),
"currently bias dtype must match output dtype ", out.dtype());
return cutlass_scaled_mm_sm75_epilogue<c2x::ScaledEpilogueBias>(
out, a, b, a_scales, b_scales, *bias);
} else {
return cutlass_scaled_mm_sm75_epilogue<c2x::ScaledEpilogue>(
out, a, b, a_scales, b_scales);
}
}
void cutlass_scaled_mm_azp_sm75(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);
if (azp) {
return cutlass_scaled_mm_sm75_epilogue<c2x::ScaledEpilogueBiasAzpToken>(
out, a, b, a_scales, b_scales, azp_adj, *azp, bias);
} else {
return cutlass_scaled_mm_sm75_epilogue<c2x::ScaledEpilogueBiasAzp>(
out, a, b, a_scales, b_scales, azp_adj, bias);
}
}
template <template <typename, typename> typename Epilogue,
typename... EpilogueArgs>
void cutlass_scaled_mm_sm80_epilogue(torch::Tensor& out, torch::Tensor const& a,
torch::Tensor const& b,
EpilogueArgs&&... epilogue_args) {
TORCH_CHECK(a.dtype() == torch::kInt8);
TORCH_CHECK(b.dtype() == torch::kInt8);
if (out.dtype() == torch::kBFloat16) {
return cutlass_gemm_sm80_dispatch<int8_t, cutlass::bfloat16_t, Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
} else {
TORCH_CHECK(out.dtype() == torch::kFloat16);
return cutlass_gemm_sm80_dispatch<int8_t, cutlass::half_t, Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
}
}
void cutlass_scaled_mm_sm80(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.dtype() == torch::kFloat32);
TORCH_CHECK(b_scales.dtype() == torch::kFloat32);
if (bias) {
TORCH_CHECK(bias->dtype() == out.dtype(),
"currently bias dtype must match output dtype ", out.dtype());
return cutlass_scaled_mm_sm80_epilogue<c2x::ScaledEpilogueBias>(
out, a, b, a_scales, b_scales, *bias);
} else {
return cutlass_scaled_mm_sm80_epilogue<c2x::ScaledEpilogue>(
out, a, b, a_scales, b_scales);
}
}
void cutlass_scaled_mm_azp_sm80(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);
if (azp) {
return cutlass_scaled_mm_sm80_epilogue<c2x::ScaledEpilogueBiasAzpToken>(
out, a, b, a_scales, b_scales, azp_adj, *azp, bias);
} else {
return cutlass_scaled_mm_sm80_epilogue<c2x::ScaledEpilogueBiasAzp>(
out, a, b, a_scales, b_scales, azp_adj, bias);
}
}
template <template <typename, typename> typename Epilogue,
typename... EpilogueArgs>
void cutlass_scaled_mm_sm89_epilogue(torch::Tensor& out, torch::Tensor const& a,
torch::Tensor const& b,
EpilogueArgs&&... epilogue_args) {
if (a.dtype() == torch::kInt8) {
TORCH_CHECK(b.dtype() == torch::kInt8);
if (out.dtype() == torch::kBFloat16) {
return cutlass_gemm_sm89_int8_dispatch<int8_t, cutlass::bfloat16_t,
Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
} else {
assert(out.dtype() == torch::kFloat16);
return cutlass_gemm_sm89_int8_dispatch<int8_t, cutlass::half_t, Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
}
} else {
TORCH_CHECK(a.dtype() == torch::kFloat8_e4m3fn);
TORCH_CHECK(b.dtype() == torch::kFloat8_e4m3fn);
if (out.dtype() == torch::kBFloat16) {
return cutlass_gemm_sm89_fp8_dispatch<cutlass::float_e4m3_t,
cutlass::bfloat16_t, Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
} else {
TORCH_CHECK(out.dtype() == torch::kFloat16);
return cutlass_gemm_sm89_fp8_dispatch<cutlass::float_e4m3_t,
cutlass::half_t, Epilogue>(
out, a, b, std::forward<EpilogueArgs>(epilogue_args)...);
}
}
}
void cutlass_scaled_mm_sm89(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.dtype() == torch::kFloat32);
TORCH_CHECK(b_scales.dtype() == torch::kFloat32);
if (bias) {
TORCH_CHECK(bias->dtype() == out.dtype(),
"currently bias dtype must match output dtype ", out.dtype());
return cutlass_scaled_mm_sm89_epilogue<c2x::ScaledEpilogueBias>(
out, a, b, a_scales, b_scales, *bias);
} else {
return cutlass_scaled_mm_sm89_epilogue<c2x::ScaledEpilogue>(
out, a, b, a_scales, b_scales);
}
}
void cutlass_scaled_mm_azp_sm89(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);
if (azp) {
return cutlass_scaled_mm_sm89_epilogue<c2x::ScaledEpilogueBiasAzpToken>(
out, a, b, a_scales, b_scales, azp_adj, *azp, bias);
} else {
return cutlass_scaled_mm_sm89_epilogue<c2x::ScaledEpilogueBiasAzp>(
out, a, b, a_scales, b_scales, azp_adj, bias);
}
}
|