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
- [Bug] Kimi-K3 AR fusion: prefill rows exceed symmetric-buffer capacity on 2-node GB300 (TP8/attn-DP2/DCP4)
- [Fix] DCP: fix RuntimeError for enable-mixed-chunk
- [Fix] hicache: preserve NVFP4 payload and scales across host transfers
- [PD] Per-backend transport interface
- [Perf] paged-experts: exact size pinning
- [Fix] scheduler: Finish aborted running requests during an in_place pause
- AMD Development Roadmap (2026 Q4)
- [Fix] serving: Return 400 for malformed requests instead of 200/500
- [Feat] weight_cache: Add protocol version checks
- [Perf] [NVIDIA] dflash: Split SWA MLA value columns on GB300
- Docs
- Python not yet supported