obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-08-22 21:50:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix][Example] Fix GCed profiling server for TPU (#12792)

Browse Source 
Signed-off-by: mgoin <[email protected]>
This commit is contained in:
Michael Goin
2025-02-13 11:52:11 +08:00
committed by GitHub
parent 4fc5c23bb6
commit d88c8666a1
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/offline_inference/profiling_tpu/profiling.py
+1 -1
View File
@@ -24,7 +24,7 @@ def main(args: argparse.Namespace):
engine_args = EngineArgs.from_cli_args(args)
llm = LLM(**dataclasses.asdict(engine_args))
_ = xp.start_server(9012)
server = xp.start_server(9012) # noqa: F841
sampling_params = SamplingParams(
temperature=0.0,