phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Fix precommit check after moving to ruff (#927)

Browse source 
Lint check in main branch is failing. This fixes the lint check after we
moved to ruff in https://github.com/meta-llama/llama-stack/pull/921. We
need to move to a `ruff.toml` file as well as fixing and ignoring some
additional checks.

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-02-02 09:46:45 -05:00 • committed by GitHub
parent 4773092dd1
commit 34ab7a3b6c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
217 changed files with 981 additions and 2681 deletions
Download patch file Download diff file Expand all files Collapse all files

24
llama_stack/providers/remote/inference/cerebras/cerebras.py
View file

@ -102,9 +102,7 @@ class CerebrasInferenceAdapter(ModelRegistryHelper, Inference):
else:
return await self._nonstream_completion(request)
async def _nonstream_completion(
self, request: CompletionRequest
) -> CompletionResponse:
async def _nonstream_completion(self, request: CompletionRequest) -> CompletionResponse:
params = await self._get_params(request)
r = await self.client.completions.create(**params)
@ -149,33 +147,23 @@ class CerebrasInferenceAdapter(ModelRegistryHelper, Inference):
else:
return await self._nonstream_chat_completion(request)
async def _nonstream_chat_completion(
self, request: CompletionRequest
) -> CompletionResponse:
async def _nonstream_chat_completion(self, request: CompletionRequest) -> CompletionResponse:
params = await self._get_params(request)
r = await self.client.completions.create(**params)
return process_chat_completion_response(r, self.formatter)
async def _stream_chat_completion(
self, request: CompletionRequest
) -> AsyncGenerator:
async def _stream_chat_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = await self._get_params(request)
stream = await self.client.completions.create(**params)
async for chunk in process_chat_completion_stream_response(
stream, self.formatter
):
async for chunk in process_chat_completion_stream_response(stream, self.formatter):
yield chunk
async def _get_params(
self, request: Union[ChatCompletionRequest, CompletionRequest]
) -> dict:
if request.sampling_params and isinstance(
request.sampling_params.strategy, TopKSamplingStrategy
):
async def _get_params(self, request: Union[ChatCompletionRequest, CompletionRequest]) -> dict:
if request.sampling_params and isinstance(request.sampling_params.strategy, TopKSamplingStrategy):
raise ValueError("`top_k` not supported by Cerebras")
prompt = ""