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

[Misc] Remove unused custom ops copy_blocks and copy_blocks_mla (#30967)

Browse Source 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
This commit is contained in:
rongfu.leng
2025-12-24 10:22:35 +08:00
committed by GitHub
parent dd424571c8
commit 4ed11105d7
6 changed files with 0 additions and 286 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
csrc/torch_bindings.cpp
View File

@@ -685,16 +685,6 @@ TORCH_LIBRARY_EXPAND(CONCAT(TORCH_EXTENSION_NAME, _cache_ops), cache_ops) {
"swap_blocks(Tensor src, Tensor! dst, Tensor block_mapping) -> ()");
cache_ops.impl("swap_blocks", torch::kCUDA, &swap_blocks);
// Copy the cache blocks from src to dst.
cache_ops.def(
"copy_blocks(Tensor(a!)[] key_caches, Tensor[](b!) value_caches, "
"Tensor block_mapping) -> ()");
cache_ops.impl("copy_blocks", torch::kCUDA, &copy_blocks);
cache_ops.def(
"copy_blocks_mla(Tensor(a!)[] kv_caches, Tensor block_mapping) -> ()");
cache_ops.impl("copy_blocks_mla", torch::kCUDA, &copy_blocks_mla);
// Reshape the key and value tensors and cache them.
cache_ops.def(
"reshape_and_cache(Tensor key, Tensor value,"