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
- [CI] runners: Isolate CI runners that share one host
- [Fix] dLLM: Reject unknown algorithm config keys
- [Fix] [NPU] qwen3-asr: Support compiled decode graph capture and replay
- [Fix] [Ascend] mooncake: Fix Mooncake TE initialization failure when use_mooncake_te is enabled
- [Feat] detokenizer: Expose router message throughput
- [Feat] [NPU] unlimited-ocr: Support Unlimited-OCR on Ascend NPUs
- [Perf] openai: extend parallel prompt encoding's intra-message cuts to Qwen2/Qwen3, o200k and DeepSeek-V3 pipelines
- [Perf] Beam search: drop the per-step blocking index copy in logits
- [Perf] kda-replayssm: Reuse the verify-fused commit step indices
- [Fix] scheduler: Reject priority requests safely with a zero queue limit
- Docs
- Python not yet supported