xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-26 08:09:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

[UX] Change kv-cache-memory log level to debug (#25479)

Browse Source 
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Michael Goin 2025-09-23 11:01:24 -04:00 committed by yewentao256
parent 2ab27b70f5
commit 02134245a9
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_worker.py
View File

@ -389,7 +389,7 @@ class Worker(WorkerBase):
f"utilize gpu memory. Current kv cache memory in use is "
f"{int(self.available_kv_cache_memory_bytes)} bytes.")
logger.info(msg)
logger.debug(msg)
# Warm up sampler and preallocate memory buffer for logits and other
# sampling related tensors of max possible shape to avoid memory