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
- [Fix] tokenizer_manager: Prevent scheduler crash and has_audio_understanding misreport for audio-declaring models without an audio tower
- [Multimodal] Return 400 for images Pillow refuses as decompression bombs
- [PD] Support runtime role switching for NIXL
- [Docs] Add three multimodal flags to the server args table
- [Fix] glm4v: Clamp request video budgets to the deployment limit
- [Bug] [diffusion] ComfyUI plugin: integrated-mode bugs in GGUF detection, import guard and VRAM accounting
- [Bug] [diffusion] OpenAI API hardening and runtime utils/pipeline bugs
- [Feature] [diffusion] ComfyUI server-mode nodes: video-to-video, audio-video output, prompt enhancement, checkpoint sweep, LoRA stacking, API recipe
- [Feature] [diffusion] ComfyUI integrated mode: support FLUX.2 and FLUX.2 Klein
- [CI] Rebuild local Rust packages in the shared Cargo cache
- Docs
- Python not yet supported