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
- [AMD] Optimize unified attention index generation and KV cache write for non-SWA models
- [ROCm] Add RDNA3 consumer GPU support (gfx1100, gfx1103)
- [Feature] Adding RISC-V Vector Extension (RVV) Attention Backend for SGLang.
- [RVV][Dockerfile] Add RVV Dockerfile, build config, and platform documentation.
- [Ngram spec v2] Precompute drafts and fully overlap
- [Feature] Add EAGLE3 speculative decoding support for Step3p5
- [sglang-miles] Improve weight checker with dtype/shape/device validation
- [alignment-sglang] PR1: TP-Invariant Kernel Layer
- [alignment-sglang] PR3: Dense Deterministic Math
- [WIP] Enable FA4 native FP8 KV cache support for MLA absorbed prefill path
- Docs
- Python not yet supported