phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 09:09:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix tgi to correctly pass llama model

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-24 21:12:57 -08:00
parent 3cace74458
commit 7e6a11d17b
1 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -89,8 +89,9 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
model = await self.model_store.get_model(model_id)
request = CompletionRequest(
model=model_id,
model=model.provider_resource_id,
content=content,
sampling_params=sampling_params,
response_format=response_format,
@ -194,8 +195,9 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
model = await self.model_store.get_model(model_id)
request = ChatCompletionRequest(
model=model_id,
model=model.provider_resource_id,
messages=messages,
sampling_params=sampling_params,
tools=tools or [],
@ -249,7 +251,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
def _get_params(self, request: ChatCompletionRequest) -> dict:
prompt, input_tokens = chat_completion_request_to_model_input_info(
request, self.formatter
request, self.register_helper.get_llama_model(request.model), self.formatter
)
return dict(
prompt=prompt,