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

16
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -176,13 +176,9 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
log.info("Sampling params: %s", sampling_params)
request_id = _random_uuid()
prompt = await chat_completion_request_to_prompt(
request, self.config.model, self.formatter
)
prompt = await chat_completion_request_to_prompt(request, self.config.model, self.formatter)
vllm_sampling_params = self._sampling_params(request.sampling_params)
results_generator = self.engine.generate(
prompt, vllm_sampling_params, request_id
)
results_generator = self.engine.generate(prompt, vllm_sampling_params, request_id)
if stream:
return self._stream_chat_completion(request, results_generator)
else:
@ -230,12 +226,8 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
)
stream = _generate_and_convert_to_openai_compat()
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 embeddings(
self, model_id: str, contents: List[InterleavedContent]
) -> EmbeddingsResponse:
async def embeddings(self, model_id: str, contents: List[InterleavedContent]) -> EmbeddingsResponse:
raise NotImplementedError()