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
- [DSpark] Fix draft MoE expert-location dispatch to restore speculative acceptance
- [HiSparse] Fix copy_cache_planned_kernel grid sizing for prefetch replay
- Fix PD streaming load tracking before dispatch
- [Fix] Bound the incremental detokenization window on a U+FFFD stream
- [EPLB] Fix dynamic expert migration for E8M0 tensors
- feat: add Seed-OSS (SeedOssForCausalLM) model support
- [PD] Move the prefill parallel-info fetch off the decode scheduler thread
- [SM12x] b12x MXFP4 MoE: align with vLLM's pin, share the arena, run W4A8
- Fix BaseConnector signal handling semantics
- [Fix] MistralDetector: no dropped calls or leaked markup in streaming
- Docs
- Python not yet supported