phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 01:42:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixes after rebase

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-12 15:37:07 -08:00
parent 948f6ece6e
commit 919d421bcf
11 changed files with 72 additions and 70 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -38,7 +38,7 @@ def build_model_aliases():
return [
build_model_alias(
model.huggingface_repo,
model.core_model_id,
model.descriptor(),
)
for model in all_registered_models()
if model.huggingface_repo
@ -85,6 +85,7 @@ class VLLMInferenceAdapter(Inference, ModelRegistryHelper, ModelsProtocolPrivate
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
model = await self.model_store.get_model(model_id)
print(f"model={model}")
request = ChatCompletionRequest(
model=model.provider_resource_id,
messages=messages,