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 7/N: BucketResolver, ordered buckets and the pick loop
- [Speculative] Avoid blocking DFlash prefill length copies
- [sgl-router] Policy reorg 8/N: wire the bucket engine behind --selection-engine reorg
- [Diffusion][MiniMax-H3] Avoid full-video clone in VAE postprocessing
- [Speculative] Share startup prefill autotuning across target modes
- [sgl-router] Policy reorg 9/N: remove the legacy selection ladder and move the bucket engine into place
- fix: prevent scheduler crash when top_logprobs exceeds vocab size
- [PD] Add CUDA-graph-compatible layer-wise NIXL transfer for hybrid attention
- [kv-shard 3/4] Enable Control Plane C
- [Fix] Reject developer messages silently omitted by chat templates
- Docs
- Python not yet supported