xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 17:35:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1] log GPU blocks num for MultiprocExecutor (#11656)

Browse Source
This commit is contained in:
WangErXiao 2025-01-04 08:13:12 +08:00 committed by GitHub
parent ad0d567e1c
commit e5d7ed0c53
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/v1/executor/multiproc_executor.py
View File

@ -95,6 +95,7 @@ class MultiprocExecutor(Executor):
Initialize the KV caches and begin the model execution loop of the
underlying workers.
"""
logger.info("# GPU blocks: %d", num_gpu_blocks)
self.collective_rpc("initialize_cache", args=(num_gpu_blocks, ))
self.collective_rpc("compile_or_warm_up_model")