[Feature] Add 'none' reasoning effort to ChatCompletionRequest#20552
Closed
Javtor wants to merge 1 commit intosgl-project:mainfrom
Closed
[Feature] Add 'none' reasoning effort to ChatCompletionRequest#20552Javtor wants to merge 1 commit intosgl-project:mainfrom
Javtor wants to merge 1 commit intosgl-project:mainfrom
Conversation
Add support for reasoning_effort='none' in the chat completions API, matching the OpenAI Python SDK's ReasoningEffort type which includes 'none' (see openai-python: types/shared/reasoning_effort.py). When reasoning_effort='none': - Sets chat_template_kwargs["thinking"] = False to disable reasoning - Sets separate_reasoning = False - Harmony path raises ValueError (same as vllm#36238) This is useful for models like Qwen3.5 that have built-in reasoning but where callers want direct output without thinking tokens.
Javtor
requested review from
CatherineSue,
JustinTong0323,
ispobock,
merrymercy and
slin1237
as code owners
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Motivation
The OpenAI Python SDK's
ReasoningEfforttype includes'none'(source), and vLLM recently added support for it (vllm#36238). SGLang currently only accepts'low','medium','high'.Modifications
python/sglang/srt/entrypoints/openai/protocol.py:"none"toreasoning_effortLiteral type"none"to thenormalize_reasoning_inputsvalidator's accepted valuesdisable_thinking_for_none_effortmodel validator that setschat_template_kwargs["thinking"] = Falseandseparate_reasoning = Falsewhenreasoning_effort == "none"python/sglang/srt/entrypoints/harmony_utils.py:"none"toget_system_messagetype hintValueErrorwhenreasoning_effort == "none"in harmony path (not supported, same approach as vLLM)Checklist
pre-commit run --all-files(no changes to formatted files)"none"with clear error