xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-09-06 07:16:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove redundant assignment in xfer_buffers, This is a little fix (#24732)

Browse Source 
Signed-off-by: ChenTaoyu-SJTU <ctynb@qq.com>
This commit is contained in:
TaoYu Chen 2025-09-13 16:11:59 +08:00 committed by GitHub
parent cfa3234a5b
commit 15b8fef453
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
View File

@ -708,8 +708,6 @@ class NixlConnectorWorker:
caches_data = [] caches_data = []
# With hybrid allocator, layers can share a kv cache tensor # With hybrid allocator, layers can share a kv cache tensor
seen_base_addresses = [] seen_base_addresses = []
xfer_buffers = (self.host_xfer_buffers
if self.use_host_buffer else kv_caches)
# Note(tms): I modified this from the original region setup code. # Note(tms): I modified this from the original region setup code.
# K and V are now in different regions. Advantage is that we can # K and V are now in different regions. Advantage is that we can