phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix server conditional awaiting on coroutines

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-08 17:03:31 -07:00
parent 216e7eb4d5
commit 8eee5b9adc
2 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/impls/meta_reference/inference/inference.py
View file

@ -34,6 +34,7 @@ class MetaReferenceInferenceImpl(Inference):
# verify that the checkpoint actually is for this model lol
async def initialize(self) -> None:
print(f"Loading model `{self.model.descriptor()}`")
self.generator = LlamaModelParallelGenerator(self.config)
self.generator.start()