phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 16:20:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refine

Browse source
This commit is contained in:
Botao Chen 2025-03-11 20:41:11 -07:00
parent cb42e1d9d4
commit 3ca640be7f
3 changed files with 7 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/remote/inference/passthrough/passthrough.py
View file

@ -94,7 +94,7 @@ class PassthroughInferenceAdapter(Inference):
client = self._get_client()
model = await self.model_store.get_model(model_id)
params = {
request_params = {
"model_id": model.provider_resource_id,
"content": content,
"sampling_params": sampling_params,
@ -103,10 +103,13 @@ class PassthroughInferenceAdapter(Inference):
"logprobs": logprobs,
}
params = {key: value for key, value in params.items() if value is not None}
request_params = {key: value for key, value in request_params.items() if value is not None}
# cast everything to json dict
json_params = self.cast_value_to_json_dict(request_params)
# only pass through the not None params
return await client.inference.completion(**params)
return await client.inference.completion(**json_params)
async def chat_completion(
self,