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
- [Deterministic][Speculative][GDN] Add Decode-Verify-Rollback
- perf: fuse GraniteMoe scaled residual RMSNorm
- feat(spec): add ECHO for EAGLE3
- [AMD] Add ROCm DWDP weight backends
- feat: support FA3 MLA decode context parallelism
- fix(function_call): use call sequence as tool_index in Glm47MoeDetector
- [Diffusion] Fix stale [T] annotation: rollout dit_trajectory timesteps is [T+1]
- [AMD] Enable aiter MLA for 12-head models via 12->16 zero-pad (Kimi-K3)
- fix(kimi-k3): mint opaque unique tool_call ids instead of positional name:ordinal
- [Attention][DCP] Add symm_a2a: single-node symmetric-memory A2A backend for MLA decode
- Docs
- Python not yet supported