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] Populate CPU mirrors for EAGLE draft extend on gpu_only batches
- [XPU][MoE] enable shared expert fusion on XPU
- fix(llama): only remap weight_scale_inv for per-tensor FP8 loading
- fix(router): reconcile Kubernetes worker discovery events
- [DSV4] Split mixed-chunk attention: route decode tokens to the fp8 paged MLA kernel
- [Fix] Redact api_key/admin_api_key/ssl_keyfile_password from server info endpoints
- fix(server_args): normalize log level before passing to uvicorn (uppercase like `WARN` silently hangs the HTTP server)
- [Perf] Do not specialize l2norm_fwd_kernel on the token count
- Kvtc RFC
- [WIP][DSV4] Breakable CUDA graph for mixed-chunk prefill
- Docs
- Python not yet supported