Skip to content

fix: remove python310 feature #963

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
shihaobai merged 1 commit into from
Jul 8, 2025
Merged

fix: remove python310 feature #963

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions lightllm/server/api_openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -386,7 +386,7 @@ async def completions_impl(request: CompletionRequest, raw_request: Request) ->


async def _process_prompts_completion(
prompts: List[str] | List[List[int]],
prompts: Union[List[str], List[List[int]]],
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Jul 8, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To improve readability and maintainability, consider defining type aliases for the complex Union types introduced in this PR. This makes the code cleaner and easier to understand, especially since Union[str, List[int]] is used in multiple function signatures.

You could define these at the module level:

PromptType = Union[str, List[int]]
PromptsType = Union[List[str], List[List[int]]]

Then you can use PromptsType here, and PromptType in the signatures of process_single_prompt and _handle_streaming_completion.

sampling_params: SamplingParams,
sampling_params_dict: Dict,
multimodal_params: MultimodalParams,
Expand All @@ -411,7 +411,7 @@ async def _process_prompts_completion(
prompts[0], sampling_params, multimodal_params, raw_request, request, created_time
)

async def process_single_prompt(prompt: str | List[int], prompt_index: int):
async def process_single_prompt(prompt: Union[str, List[int]], prompt_index: int):
if len(prompts) > 1:
individual_sampling_params = SamplingParams()
individual_sampling_params.init(tokenizer=g_objs.httpserver_manager.tokenizer, **sampling_params_dict)
Expand All @@ -437,7 +437,7 @@ async def process_single_prompt(prompt: str | List[int], prompt_index: int):


async def _handle_streaming_completion(
prompt: str | List[int],
prompt: Union[str, List[int]],
sampling_params: SamplingParams,
multimodal_params: MultimodalParams,
raw_request: Request,
Expand Down