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] Gemma-4-31B QAT W4A16 CT fails gptq_marlin_repack on SM121
- Fix cross-stream ordering races in spec-v2 overlap plan stream
- [Bug] Prometheus /metrics scrape can starve prefill bootstrap health checks
- docs(cookbook): migrate GLM-5.1 to the config-driven template
- docs(cookbook): migrate Nemotron3-Ultra to the config-driven template
- docs(cookbook): migrate MiniMax-M2.7 to the config-driven template
- fix: zero uninitialized FA3 padding output in DP attention SUM_LEN mode
- [scheduler] Publish per-scheduler load on a dedicated socket for load-aware routers
- [diffusion][ROCm][Perf]: Set gfx942 AITER FMHA rounding mode to rtz instead of rtna
- [diffusion] Continuous batching v0
- Docs
- Python not yet supported