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
- Apertus2509Detector (streaming) drops the second tool block and trailing text when they arrive in the same chunk`
- fix(diffusion): honor Hunyuan3D paint remeshing configuration
- fix(function_call): process all buffered Apertus tool blocks on stream end
- fix(function_call): recognize abbreviated Harmony commentary header in gpt-oss detector
- [Spec] Opt-in int8 weights for DFLASH and DSpark draft linears
- [Bug] PEFT adapters with bias="lora_only" or "all" crash or silently corrupt weights during normalize_qkv_proj
- [diffusion] kernels: take the Wan VAE decoder's remaining first-decode work off the request path
- fix(anthropic): report matched stop sequences
- [diffusion] conditioning cache: recycle warmup-only entries at the first served store
- [diffusion] warm the image writer and the HTTP route models at startup
- Docs
- Python not yet supported