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
- [DSv4.1] Enable DeepGEMM sparse prefill under CP
- [Intel GPU] Dispatch the DeepSeek V4 attention metadata ops on XPU
- [Intel GPU] Dequantize dense block-fp8 weights to bf16 at load
- [AMD][Feature] enable triton TLX
- [Qwen4-Exp] Pin the PLE host table at its exact size
- Fix NUMA wrapper execution on noexec filesystems
- feat: support strict MiMo-V2.6 tool calling with XGrammar
- Fix preferred_sampling_params being clobbered by unset request fields
- Retry the post-warmup freeze_gc while the listener is still coming up
- [GDN] Route SM100 FlashInfer MTP verify through the public pretranspose dispatch
- Docs
- Python not yet supported