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
- [sgl-router] Policy reorg 1/N: move KV-event and load state under policies/state
- [sgl-router] Policy reorg 2/N: extract the load view from admission.rs
- fix(router): keep DeepSeek V4.1 prompts worker-encoded
- [PD][NPU] Fix Mooncake TE init failure caused by thread-local ACL device binding
- [Perf] Qwen MoE: single-launch fused shared-expert gate via aiter top…
- [AMD][CI] Restore AMD registrations dropped by #37436 and fix the 3FS hicache suite
- fix: substitute image placeholder for glm5 next multimodal reminder
- [Fix] Bound reasoning state decompression
- [Fix] Limit decompressed request body size
- Release fastsafetensors file buffers after each shard
- Docs
- Python not yet supported