xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 06:45:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Improve memory profiling debug message (#21429)

Browse Source 
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
This commit is contained in:
Ye (Charlotte) Qi 2025-07-26 07:07:21 -07:00 committed by GitHub
parent c215f5c877
commit a40a8506df
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 14 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
vllm/v1/worker/gpu_worker.py
View File

@ -246,11 +246,21 @@ class Worker(WorkerBase):
available_kv_cache_memory = self.requested_memory \
- profile_result.non_kv_cache_memory
unrequested_memory = self.init_snapshot.free_memory \
- self.requested_memory
logger.debug(
"Initial free memory: %.2f GiB, free memory: %.2f GiB, "
"requested GPU memory: %.2f GiB",
GiB(self.init_snapshot.free_memory), GiB(free_gpu_memory),
GiB(self.requested_memory))
"Initial free memory: %.2f GiB; "
"Requested memory: %.2f (util), %.2f GiB",
GiB(self.init_snapshot.free_memory),
self.cache_config.gpu_memory_utilization,
GiB(self.requested_memory),
)
logger.debug(
"Free memory after profiling: %.2f GiB (total), "
"%.2f GiB (within requested)",
GiB(free_gpu_memory),
GiB(free_gpu_memory - unrequested_memory),
)
logger.debug(profile_result)
logger.info("Available KV cache memory: %.2f GiB",
GiB(available_kv_cache_memory))