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
- [Diffusion][SenseNova] prefix kv reuse for n>1 requests
- [BugFix] Fail fast when AutoProcessor degrades to bare tokenizer for multimodal model (#39831)
- fix(disagg): wait for every NIXL state component per rank
- perf(hicache, hybrid): Full-KV prefetch anchor, eager Mamba L3 write, independent host Mamba pool ratio
- Add optional strip layout for Inkling speculative convolutions
- Amd/topk v2 prefill packed kernel
- [diffusion] perf: replay hot Triton launches from Rust
- pp mtp support mimo
- [Bug] Potential DSpark startup hang from an unsynchronized CUDA graph memory check
- [Bugfix] Keep chat stream IDs and timestamps consistent
- Docs
- Python not yet supported