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] spark25: Preserve nullable tool argument types
- [Perf] kda: Fuse QKV preparation and QK L2 normalization
- [Feat] [NPU] dsv4: A5 explicit-state bring-up and position-addressed C4 state on PD
- [Feat] [NPU] memory-saver: Release device communication domains on sleep mode
- [Fix] kimi_k3: Use uuid tool_call_id instead of history-count id
- [Perf] moe: Fuse GLM clamp SwiGLU and FP8 activation quantization
- [Feat] moe: Integrate EvenMoE expert placement and replica routing
- [Feat] sail: support sail fa3 and flashmla [3/N]
- [CI] slash-command: Drive opt-in CI tiers from a registry
- [Feat] checkpoint: Process checkpoint lifecycle with prepare/status/resume routes
- Docs
- Python not yet supported