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

36
llama_stack/providers/inline/inference/meta_reference/parallel_utils.py
View file

@ -55,47 +55,33 @@ class ProcessingMessageName(str, Enum):
class ReadyRequest(BaseModel):
type: Literal[ProcessingMessageName.ready_request] = (
ProcessingMessageName.ready_request
)
type: Literal[ProcessingMessageName.ready_request] = ProcessingMessageName.ready_request
class ReadyResponse(BaseModel):
type: Literal[ProcessingMessageName.ready_response] = (
ProcessingMessageName.ready_response
)
type: Literal[ProcessingMessageName.ready_response] = ProcessingMessageName.ready_response
class EndSentinel(BaseModel):
type: Literal[ProcessingMessageName.end_sentinel] = (
ProcessingMessageName.end_sentinel
)
type: Literal[ProcessingMessageName.end_sentinel] = ProcessingMessageName.end_sentinel
class CancelSentinel(BaseModel):
type: Literal[ProcessingMessageName.cancel_sentinel] = (
ProcessingMessageName.cancel_sentinel
)
type: Literal[ProcessingMessageName.cancel_sentinel] = ProcessingMessageName.cancel_sentinel
class TaskRequest(BaseModel):
type: Literal[ProcessingMessageName.task_request] = (
ProcessingMessageName.task_request
)
type: Literal[ProcessingMessageName.task_request] = ProcessingMessageName.task_request
task: Union[CompletionRequestWithRawContent, ChatCompletionRequestWithRawContent]
class TaskResponse(BaseModel):
type: Literal[ProcessingMessageName.task_response] = (
ProcessingMessageName.task_response
)
type: Literal[ProcessingMessageName.task_response] = ProcessingMessageName.task_response
result: TokenResult
class ExceptionResponse(BaseModel):
type: Literal[ProcessingMessageName.exception_response] = (
ProcessingMessageName.exception_response
)
type: Literal[ProcessingMessageName.exception_response] = ProcessingMessageName.exception_response
error: str
@ -189,9 +175,7 @@ def retrieve_requests(reply_socket_url: str):
group=get_model_parallel_group(),
)
if isinstance(updates[0], CancelSentinel):
log.info(
"quitting generation loop because request was cancelled"
)
log.info("quitting generation loop because request was cancelled")
break
if mp_rank_0():
@ -350,9 +334,7 @@ class ModelParallelProcessGroup:
def run_inference(
self,
req: Union[
CompletionRequestWithRawContent, ChatCompletionRequestWithRawContent
],
req: Union[CompletionRequestWithRawContent, ChatCompletionRequestWithRawContent],
) -> Generator:
assert not self.running, "inference already running"