phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-19 00:49:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into henrytu/cerebras-integration

Browse source
This commit is contained in:
Henry Tu 2024-12-02 10:57:59 -05:00 • committed by GitHub
commit c29e3271d3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
38 changed files with 523 additions and 139 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/nvidia/config.py
View file

@ -35,7 +35,9 @@ class NVIDIAConfig(BaseModel):
"""
url: str = Field(
default="https://integrate.api.nvidia.com",
default_factory=lambda: os.getenv(
"NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"
),
description="A base url for accessing the NVIDIA NIM",
)
api_key: Optional[str] = Field(

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,