phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 17:29:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Minor change to force rerun of automatic jobs

Browse source
This commit is contained in:
Fred Reiss 2024-12-19 15:06:47 -08:00
parent c8580d3b0c
commit 82c10c917f
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -78,7 +78,7 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
self.engine = AsyncLLMEngine.from_engine_args(engine_args) self.engine = AsyncLLMEngine.from_engine_args(engine_args)
async def shutdown(self): async def shutdown(self):
"""Shutdown the vLLM inference adapter.""" """Shut down the vLLM inference adapter."""
log.info("Shutting down vLLM inference provider.") log.info("Shutting down vLLM inference provider.")
if self.engine: if self.engine:
self.engine.shutdown_background_loop() self.engine.shutdown_background_loop()