biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047)

Browse Source
This commit is contained in:
bnellnm
2024-06-09 16:23:30 -04:00
committed by GitHub
parent 5d7e3d0176
commit 5467ac3196
55 changed files with 833 additions and 451 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/quantization/aqlm/gemm_kernels.cu
View File

@@ -18,7 +18,7 @@
#include <cuda.h>
#include <cuda_fp16.h>
#include <cuda_runtime.h>
#include <torch/extension.h>
#include <torch/all.h>
#include <c10/cuda/CUDAStream.h>
#include <c10/cuda/CUDAGuard.h>