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
- docs(sgl-model-gateway): add DaoXE OpenAI-compatible upstream example
- Add optional uint16/uint8 routed-experts wire encoding
- ci: bound nvidia-smi in detect_host so a wedged driver fails fast
- [FIX] Integrate embedding KV-cache-skip fast path into torch_native backend
- [Feature] Support Deterministic Inference for Qwen3_5ForConditionalGeneration
- fix(fastapi routes): skip path-less routes in _get_fastapi_request_path
- [Fix] Resolve object-storage URI for model_name in get_processor
- [AMD] Fix packed DSA FP8 KV write routing on HIP
- fix(function_call): don't leak partial bot_token bytes in DeepSeek V3/V3.1 streaming detectors
- Fix multimodal input path crashes on non-CUDA machines
- Docs
- Python not yet supported