xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-28 07:37:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-01-01 18:44:21 -08:00
parent ba64a0249f
commit 1ca4298b9b
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_block_table.py
View File

@ -41,7 +41,7 @@ class BlockTable:
self.num_blocks_per_row = np.zeros((max_num_reqs,), dtype=np.int32) self.num_blocks_per_row = np.zeros((max_num_reqs,), dtype=np.int32)
# UVA requires pinned memory. # UVA requires pinned memory.
self.use_uva = is_uva_available() and pin_memory and False self.use_uva = is_uva_available() and pin_memory
if self.use_uva: if self.use_uva:
logger.info("Using Unified Virtual Addressing (UVA) for block " logger.info("Using Unified Virtual Addressing (UVA) for block "
"table transfer.") "table transfer.")