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
- [Fix] scheduler: Bind request receivers to their selected transport
- [Feat] engram: Prototype remote shared table lookup
- [Fix] diffusion: Enforce Pika H3 Flex release policies
- [Test] diffusion/disaggregation: Cover aligned transfer staging
- [Fix] profiler: Init profile-by-stage counters when num_steps is not given
- [Feat] paged-experts: size the resident experts automatically
- [Feat] [NPU] attention: support mixed-chunk on the ascend attention backend
- [Doc] ascend: add NPU graph mode optimization guide
- [Doc] cookbook: add Ascend NPU deployment for Qwen3
- SGLANG_JIT_DEEPGEMM_FAST_WARMUP on DeepSeek-V4.1: 3-5x faster cold start, no runtime degradation detectable at chunked-prefill 16384
- Docs
- Python not yet supported