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] Qwen3.5 visual encoder weights dropped by PP layer-range filter in load_weights
- [Fix][DeepSeek V4] DSpark crash when CLI block size overrides config
- [diffusion] vae: retry decode with tiling once on OOM instead of failing
- [Hicache] Support Mamba branching setting by env
- [AMD][DI][CI] 10/N Add DSV4 HiSparse+HiCache 1P1D nightly recipes (FP4/FP8) x (PRO/FLASH)
- [Bugfix] Preserve Qwen3.5 encoder weights under PP
- fix(quant): load mixed-precision compressed-tensors W4A8-FP8 checkpoints
- perf(attention): adapt TRTLLM MHA scheduling for ragged decode
- [CI][RFC] Persist black's formatting cache across lint runs (alternative to #37210)
- [Bug] --dp 8 intermittently fails with TCPStore EADDRINUSE on single-node 8×H800
- Docs
- Python not yet supported