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] Security Report
- [AMD] Use SHUFFLE KV and AITER sparse attention for MiniMax-M3
- [Bug] Serving benchmark includes unmeasured zero TTFTs in latency statistics
- [Bugfix] Exclude unmeasured TTFTs from serving benchmark statistics
- [XPU] Upgrade XPU backend to PyTorch 2.14
- [DSA] Prefill indexer: TP row split and per-request page-table rows (opt-in)
- [AMD][Diffusion] Run residual_gate_add Triton kernels on ROCm without PTX
- [HiCache] MLA/DSA host dedup with rotating layer owners, chunked D2H backup issue and idle-sync skip (opt-in)
- [WIP] rocm 101 rc
- [AMD] GLM-5.3-Flash mHC decode: fuse FFN all-reduce into hc_post
- Docs
- Python not yet supported