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

chore: enable pyupgrade fixes (#1806)

Browse source 
# What does this PR do?

The goal of this PR is code base modernization.

Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)

Note to reviewers: almost all changes here are automatically generated
by pyupgrade. Some additional unused imports were cleaned up. The only
change worth of note can be found under `docs/openapi_generator` and
`llama_stack/strong_typing/schema.py` where reflection code was updated
to deal with "newer" types.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
This commit is contained in:
Ihar Hrachyshka 2025-05-01 17:23:50 -04:00 • committed by GitHub
parent ffe3d0b2cd
commit 9e6561a1ec
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
319 changed files with 2843 additions and 3033 deletions
Download patch file Download diff file Expand all files Collapse all files

68
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -6,7 +6,7 @@
import asyncio
import os
from typing import AsyncGenerator, List, Optional, Union
from collections.abc import AsyncGenerator
from pydantic import BaseModel
from termcolor import cprint
@ -184,11 +184,11 @@ class MetaReferenceInferenceImpl(
self,
model_id: str,
content: InterleavedContent,
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> Union[CompletionResponse, CompletionResponseStreamChunk]:
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> CompletionResponse | CompletionResponseStreamChunk:
if sampling_params is None:
sampling_params = SamplingParams()
if logprobs:
@ -215,11 +215,11 @@ class MetaReferenceInferenceImpl(
async def batch_completion(
self,
model_id: str,
content_batch: List[InterleavedContent],
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
content_batch: list[InterleavedContent],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> BatchCompletionResponse:
if sampling_params is None:
sampling_params = SamplingParams()
@ -291,14 +291,14 @@ class MetaReferenceInferenceImpl(
for x in impl():
yield x
async def _nonstream_completion(self, request_batch: List[CompletionRequest]) -> List[CompletionResponse]:
async def _nonstream_completion(self, request_batch: list[CompletionRequest]) -> list[CompletionResponse]:
tokenizer = self.generator.formatter.tokenizer
first_request = request_batch[0]
class ItemState(BaseModel):
tokens: List[int] = []
logprobs: List[TokenLogProbs] = []
tokens: list[int] = []
logprobs: list[TokenLogProbs] = []
stop_reason: StopReason | None = None
finished: bool = False
@ -349,15 +349,15 @@ class MetaReferenceInferenceImpl(
async def chat_completion(
self,
model_id: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
tool_config: Optional[ToolConfig] = None,
messages: list[Message],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
tools: list[ToolDefinition] | None = None,
tool_choice: ToolChoice | None = ToolChoice.auto,
tool_prompt_format: ToolPromptFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
tool_config: ToolConfig | None = None,
) -> AsyncGenerator:
if sampling_params is None:
sampling_params = SamplingParams()
@ -395,13 +395,13 @@ class MetaReferenceInferenceImpl(
async def batch_chat_completion(
self,
model_id: str,
messages_batch: List[List[Message]],
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
tool_config: Optional[ToolConfig] = None,
messages_batch: list[list[Message]],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
tools: list[ToolDefinition] | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
tool_config: ToolConfig | None = None,
) -> BatchChatCompletionResponse:
if sampling_params is None:
sampling_params = SamplingParams()
@ -436,15 +436,15 @@ class MetaReferenceInferenceImpl(
return BatchChatCompletionResponse(batch=results)
async def _nonstream_chat_completion(
self, request_batch: List[ChatCompletionRequest]
) -> List[ChatCompletionResponse]:
self, request_batch: list[ChatCompletionRequest]
) -> list[ChatCompletionResponse]:
tokenizer = self.generator.formatter.tokenizer
first_request = request_batch[0]
class ItemState(BaseModel):
tokens: List[int] = []
logprobs: List[TokenLogProbs] = []
tokens: list[int] = []
logprobs: list[TokenLogProbs] = []
stop_reason: StopReason | None = None
finished: bool = False