@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / d88c8666a1
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 15, 23:30 UTC

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

Signed-off-by: mgoin <michael@neuralmagic.com>

Michael Goin committed Feb 12, 2025 at 22:52 UTC d88c8666a167c97193cb3d48fd2de3d90b5b8d85
1 file changed +1 -1
examples/offline_inference/profiling_tpu/profiling.py
+1 -1
@@ -24,7 +24,7 @@ def main(args: argparse.Namespace):
24
25 engine_args = EngineArgs.from_cli_args(args)
26 llm = LLM(**dataclasses.asdict(engine_args))
27 - _ = xp.start_server(9012)
27 + server = xp.start_server(9012) # noqa: F841
28
29 sampling_params = SamplingParams(
30 temperature=0.0,