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

12
llama_stack/providers/remote/inference/runpod/runpod.py
View file

@ -45,9 +45,7 @@ RUNPOD_SUPPORTED_MODELS = {
class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
def __init__(self, config: RunpodImplConfig) -> None:
ModelRegistryHelper.__init__(
self, stack_to_provider_models_map=RUNPOD_SUPPORTED_MODELS
)
ModelRegistryHelper.__init__(self, stack_to_provider_models_map=RUNPOD_SUPPORTED_MODELS)
self.config = config
self.formatter = ChatFormat(Tokenizer.get_instance())
@ -104,9 +102,7 @@ class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
r = client.completions.create(**params)
return process_chat_completion_response(r, self.formatter)
async def _stream_chat_completion(
self, request: ChatCompletionRequest, client: OpenAI
) -> AsyncGenerator:
async def _stream_chat_completion(self, request: ChatCompletionRequest, client: OpenAI) -> AsyncGenerator:
params = self._get_params(request)
async def _to_async_generator():
@ -115,9 +111,7 @@ class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
yield chunk
stream = _to_async_generator()
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
def _get_params(self, request: ChatCompletionRequest) -> dict: