biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: mgoin <michael@neuralmagic.com>
This commit is contained in:
Michael Goin
2025-02-12 22:52:11 -05:00
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

2
examples/offline_inference/profiling_tpu/profiling.py
View File

@@ -24,7 +24,7 @@ def main(args: argparse.Namespace):
engine_args = EngineArgs.from_cli_args(args) engine_args = EngineArgs.from_cli_args(args)
llm = LLM(**dataclasses.asdict(engine_args)) llm = LLM(**dataclasses.asdict(engine_args))
_ = xp.start_server(9012) server = xp.start_server(9012) # noqa: F841
sampling_params = SamplingParams( sampling_params = SamplingParams(
temperature=0.0, temperature=0.0,