xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-14 00:25:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] remove old comments (#4866)

Browse Source
This commit is contained in:
youkaichao 2024-05-16 11:07:41 -07:00 committed by GitHub
parent e08188081b
commit 10fa9eea21
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/worker/model_runner.py
View File

@ -887,16 +887,6 @@ class ModelRunner:
# This usually takes < 10 seconds. # This usually takes < 10 seconds.
logger.info("Graph capturing finished in %.0f secs.", elapsed_time) logger.info("Graph capturing finished in %.0f secs.", elapsed_time)
def __del__(self) -> None:
# Delete the CUDA graphs before deleting the pynccl communicator.
# NOTE(woosuk): This is necessary because otherwise deadlocks can
# happen.
# FIXME(woosuk): This is a bit hacky. Find a more robust solution.
# TODO(youkaichao): when we get enough user feedback that pynccl is
# more stable than cupy, we can remove this, e.g. in v0.4.1.
self.graph_runners.clear()
self.pynccl_backend = None
@property @property
def vocab_size(self) -> int: def vocab_size(self) -> int:
return self.model_config.get_vocab_size() return self.model_config.get_vocab_size()