@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 6d2f74efb3
Fork 0

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, 09:15 UTC

Remove redundant fn

Woosuk Kwon committed Feb 16, 2023 at 09:24 UTC 6d2f74efb34566edc11477a651749173cac4c25d
1 file changed +1 -8
csrc/cache.cpp
+1 -8
@@ -5,16 +5,9 @@ void copy_blocks(
5 torch::Tensor& dst,
6 const std::map<int64_t, int64_t>& block_mapping);
7
8 -void copy_cache_blocks(
9 - torch::Tensor& src,
10 - torch::Tensor& dst,
11 - const std::map<int64_t, int64_t>& block_mapping) {
12 - copy_blocks(src, dst, block_mapping);
13 -}
14 -
8 PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
9 m.def(
10 "copy_cache_blocks",
18 - &copy_cache_blocks,
11 + &copy_blocks,
12 "Copy the cache blocks from src to dst");
13 }