xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-05 17:15:44 +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 Initialize the KV caches and begin the model execution loop of the
underlying workers. underlying workers.
""" """
logger.info("# GPU blocks: %d", num_gpu_blocks)
self.collective_rpc("initialize_cache", args=(num_gpu_blocks, )) self.collective_rpc("initialize_cache", args=(num_gpu_blocks, ))
self.collective_rpc("compile_or_warm_up_model") self.collective_rpc("compile_or_warm_up_model")