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 Qwen3 Coder stalls on large string tool arguments
- fix(hicache): scope write-back load-back pins by component
- [AMD] Reuse DSV4 logits workspace for long contexts
- [diffusion][Model] Support MAGI-2-preview
- fix(npu): split packed MTP HiCache transfers by pool
- [diffusion][Model] Support MAGI-2-preview
- [Fix] Llama4 NVFP4 checkpoint loading: fused expert scales and packed q/k permute
- [VLM][EPD] Reuse Kimi-K3 embeddings before encoder preprocessing
- [VLM] Add preprocess-cache observability and agentic benchmark coverage
- [Model] Add native SenseNova U1 multimodal generation and interleave serving
- Docs
- Python not yet supported