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] Mooncake HiCache backup fails for Qwen3.8-Flash-Next-FP8
- [Test] [NPU] rl: Add sleep/wake scheduler unit and 1-NPU smoke tests
- [Bug] --tool-call-parser auto finds no parser on Qwen2.5-0.5B, Qwen3 2507 and Ling-mini-2.0, so tool calls come back as text
- [Test] elastic-ep: Register NIXL EP CI coverage
- [Fix] offloader: Enforce the CPU offload storage budget
- [Perf] [AMD] DeepSeek-V4.1: Shard the HIP prefill indexer rows across attention TP
- [Feat] serving: Add --max-payload-size flag to raise the HTTP request payload limit
- [CI] diffusion: Wan VAE decode time spikes on the 1-gpu-5090 sm* runners
- [Feat] [Intel] Model-enabling: Enable Nemotron-H models on Xeon CPU
- [Bug] disaggregation: Qwen EAGLE PD decode can produce corrupted output after retraction
- Docs
- Python not yet supported