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
- [Feature] Dynamic verification for DFlash2
- [MoonEP] Fix BF16 physical row semantics and unsupported config checks
- [XPU] Support DeepEP expert parallelism on Intel XPU
- feat(quant): support compressed-tensors quantized embed_tokens
- perf(kimi-k3): add the B300 SP-collective tuning table
- [PD] Support heterogeneous TP/PP KV cache transfer with Mooncake reshard
- fix(function-call): preserve text after DeepSeek tool calls
- [EPD] Overlap multimodal preprocessing with ViT execution
- [Fix] Qwen3.5 MTP: ask the checkpoint whether mtp.* is quantized
- [EPD] Avoid redundant CPU embedding materialization in the unpooled ZMQ path
- Docs
- Python not yet supported