frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix missing removal

Browse Source 
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
This commit is contained in:
Zhuohan Li
2025-10-17 11:35:42 -07:00
parent 3fd66b1e73
commit a2599dca0f
1 changed files with 2 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py
View File

@ -174,12 +174,10 @@ class SharedStorageConnector(KVConnectorBase_V1):
# Only process layers that have kv_cache # Only process layers that have kv_cache
# attribute (attention layers) Skip non-attention # attribute (attention layers) Skip non-attention
# layers like FusedMoE/MLP etc. # layers like FusedMoE/MLP etc.
kv_cache_attr = getattr(layer, "kv_cache", None) kv_cache_layer = getattr(layer, "kv_cache", None)
if kv_cache_attr is None: if kv_cache_layer is None:
continue continue
kv_cache_layer = kv_cache_attr[forward_context.virtual_engine]
filename = self._generate_filename_debug( filename = self._generate_filename_debug(
layer_name, request.token_ids, request.mm_hashes layer_name, request.token_ids, request.mm_hashes
) )