xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-08 13:47:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-09-18 15:51:36 -07:00
parent a98eff0762
commit 323a05b3c5
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/gpu/attn_utils.py
View File

@ -136,4 +136,4 @@ def init_kv_cache(
kv_cache_raw_tensors = _allocate_kv_cache(kv_cache_config, device)
kv_caches = _reshape_kv_cache(kv_cache_config, kv_cache_raw_tensors,
attn_backends)
bind_kv_cache(forward_context, kv_caches, runner_kv_caches)
bind_kv_cache(kv_caches, forward_context, runner_kv_caches)