sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [Fix] Preserve the SWA window of short prefill extends under DeepSeek-V4.1 decoder bounded replay
- fix: tolerate parent exit during multimodal process cleanup
- [Bugfix] Stream Qwen3 Coder string tool arguments incrementally
- [Bug] gpt-oss detector misses tool calls that are the first message or lack <|constrain|>json
- [Bug] Gemma4Detector returns null and exponent-notation numbers as strings
- [Bug] DeepSeek V3.2/V4 DSML detector strips whitespace (e.g. trailing newline) from string="true" parameter values
- fix(function_call): keep whitespace in deepseekv32/v4 string param values
- fix(function_call): Gemma4Detector parses null and exponent-notation numbers
- fix(function_call): gpt-oss detects first-message and constrain-less calls
- fix(openai): cache negative byte-level tokenizer verdicts in logprob bytes
- Docs
- Python not yet supported