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
- [Spec][DSV4] perf: Skip unused draft metadata
- [Bugfix] Fix Qwen3.5 DFlash aux capture
- [Spec][DSV4] perf: Compile draft hc_head during CUDA graph capture
- fix(model): apply Gemma4 local/global head-dim remap to standalone gemma4_text configs
- Expose accelerator name in /v1/loads JSON
- [Feature] Support aborting requests by rid prefix
- [LoRA] Support upsert when loading adapters from distributed
- [LoRA] Fix gated MoE-LoRA under virtual experts; compressed-tensors runner detection and EP expert map
- fix(gemma4): validate precomputed image token counts
- [Fix] Strip whitespace when parsing legacy and Envs boolean/int fields
- Docs
- Python not yet supported