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
- feat: separate image loader
- [NPU] Support LongCat 2.0 for Ascend NPU
- refactor: make time_stats msgpack-native
- [AMD][Mori] Enable Kimi K2.6 wideEP -- Add deepep_normal<->triton MoE permute for wide-EP (mori)
- [Feature] OSCAR mixed-precision INT2 KV cache (--kv-cache-dtype int2)
- fix(gateway): reconcile k8s service discovery with periodic full LIST
- [Bug] Generation health checks can perturb DP user routing state and collapse long-prefill throughput
- trace: split decoder bootstrap and KV allocation wait
- [Apple Silicon] Add an architecture-independent ATen-to-MLX lowering layer
- [CI][Ascend] Fix plog persistence and add debug-only nightly perf suite for DeepSeek-V4-Flash
- Docs
- Python not yet supported