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
- ©_cache_blocks,
11
+ ©_blocks,
12
"Copy the cache blocks from src to dst");
13
}