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
- [HiCache] Serve host-tier prefix hits for DeepSeek-V4 with encoder SWA bounded replay
- [DSpark] Keep TP ranks planning the same verify budget under overlap scheduling
- [DSv4.1] Let DSpark compact verify run on DeepSeek-V4.1 by mapping packed verify tokens to their requests
- [DeepSeek-V4] Reject prompt-logprob requests at admission under decoder SWA bounded replay instead of crashing the server
- Fix Llama3 Nemotron Parser
- [XPU] Fix SWA paged allocator
- perf(kimi-k3): prepare native MXFP4 expert-tile routing in the fused route+quant launch
- [SMG] Forward decode streams while prefill is still running
- [AMD] AgentX draft slot 1
- [AMD] AgentX draft slot 2
- Docs
- Python not yet supported