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
- [AMD] DO NOT MERGE - add config-driven nightly serving-benchmark workflow
- fix(router): drop upstream Content-Length when forwarding response headers
- [HiCache][UnifiedTree] L3 SWA periodic checkpoint
- [Bug] Fix AttributeError when chunked prefill encounters EVSEmbeddingResult
- [diffusion][ROCm][Perf]: Enable BF16 attention and MXFP4 compilation on ROCm
- [diffusion] Update LingBot-World chunk-size through webui
- [WIP] Enable FlashInfer GDN pool-indexed decode and bf16 state on SM90
- [JIT Kernel] Fused Add+RMSNorm+per-token FP8 quant: enable for checkpoint-quantized models, wire RMSNorm, validate (revives #22005)
- fix(openai): return real HTTP status for pre-stream admission aborts
- Fix SGLANG_DEFAULT_THINKING ignored by dsv4/dsv32 reasoning parser
- Docs
- Python not yet supported