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
- [Bug] Deterministic sampling rejects min-p requests with a seed
- [Bug] Concurrent pause and continue requests can orphan a tokenizer worker waiter
- [Bug] Concurrent paused weight updates share completion state
- [Bugfix] Support deterministic min-p sampling with a seed
- [Bugfix] Scope pause/continue completion by operation
- [PP] Commit the proxy send after launching the next forward
- [Feature] [Diffusion] Overlap Ulysses A2A with attention compute for Wan2.2-TI2V-5B
- [Bugfix] Fix Responses API crash on Harmony preamble messages
- [diffusion] pipeline: support SelfLift progressive resolution
- [AMD gfx950] AttnResidual score kernel: ASM DPP+LDS, +84% vs Triton
- Docs
- Python not yet supported