[CI/Build] Per file CUDA Archs (improve wheel size and dev build times) (#8845)

This commit is contained in:
Lucas Wilkinson
2024-10-03 22:55:25 -04:00
committed by GitHub
parent 3dbb215b38
commit aeb37c2a72
22 changed files with 828 additions and 370 deletions
+6
View File
@@ -22,6 +22,8 @@
#include "../gptq_marlin/marlin.cuh"
#include "../gptq_marlin/marlin_dtypes.cuh"
#include "core/registration.h"
using namespace marlin;
#define STATIC_ASSERT_SCALAR_TYPE_VALID(scalar_t) \
@@ -1303,3 +1305,7 @@ torch::Tensor fp8_marlin_gemm(torch::Tensor& a, torch::Tensor& b_q_weight,
}
#endif
TORCH_LIBRARY_IMPL_EXPAND(TORCH_EXTENSION_NAME, CUDA, m) {
m.impl("fp8_marlin_gemm", &fp8_marlin_gemm);
}