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
- [AMD][HiSparse][HiCache][PD] Give the transfer kernels a device alias for host-registered pools
- fix(qsa): fail early on SM89 without classic FA2
- feat(rust-server): support OpenAI embedding requests
- [MoE][Ada] Add Qwen4-Exp FP8 Triton configs for NVIDIA L20
- [Bug] quantization: drop dead 'marlin' --quantization CLI choice
- [NPU]Add NPU test suites for linear attn verify, SMG gRPC mode and disaggregation extra slots.
- [Bug] Prefill transfer failed with exception KVTransferError Decode instance could be dead, remote mooncake session ...:port is not alive
- [BugFix] Handle CPU-only and XPU environments in check_env
- [comm] Rebuild the custom all-reduce v2 dispatch layer
- Accept every LoRA target module the runtime already supports
- Docs
- Python not yet supported