A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 00:30 UTC
[Misc] Remove unused cuda_utils.h in CPU backend (#5345)
Jie Fu (傅杰) committed
Jun 8, 2024 at 05:09 UTC
6840a716104c8c17303b938673c2ac019e541700
1 file changed
-1
csrc/cpu/pybind.cpp
-1
@@ -1,5 +1,4 @@
1
#include "cache.h"
2
-#include "cuda_utils.h"
2
#include "ops.h"
3
#include <torch/extension.h>
4