frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 23:03:52 +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>
This commit is contained in:
Michael Goin
2025-09-23 11:01:24 -04:00
committed by GitHub
parent 4c966e440e
commit 2c58742dff
1 changed files with 1 additions and 1 deletions
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"utilize gpu memory. Current kv cache memory in use is "
f"{int(self.available_kv_cache_memory_bytes)} bytes.") 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 # Warm up sampler and preallocate memory buffer for logits and other
# sampling related tensors of max possible shape to avoid memory # sampling related tensors of max possible shape to avoid memory