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
- [diffusion] Make warmup preload components and margin configurable
- Batch image outputs in server mode
- Pd role switch
- [perf] Reduce `import sglang` time by lazily importing video decoder
- [Perf] Reduce KV-cache gather overhead in DCP MLA prefill
- [Bug] DeepSeekV3Detector streaming drops the first tool call when two complete calls arrive in one increment
- [Diffusion] Add opt-in pi0.5 completion-boundary action batching
- [HiCache] Inject random delays and failures for testing
- [Fix] Restore previous checkpoint after failed disk weight updates
- [Bug] CUDA VMM multimodal transport slice leaks when a request is aborted while still queued
- Docs
- Python not yet supported