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
- [Session] Remove unused capacity_of_str_len parameter
- Fix/compressed tensors nvfp4 hopper
- fix: resolve issue 39971
- [Fix] Order EAGLE draft-extend planning after input producers
- perf(xpu): promote MXFP4 MoE bias to fp32 at load, not per forward
- [Router] Readiness as a first-class worker state
- fix: resolve cache_creation_input_tokens reporting in anthropic endpoint
- [Session] Ignore unused Mamba slots during cleanup
- [MLX] Fix cache accounting during chained decode
- Fix DSA indexer metadata not fetched on breakable decode CUDA graph
- Docs
- Python not yet supported