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
- dp-attention: add prefix_affinity load balancing for routing-key/session affinity
- fix(bcg): preserve Qwen3-VL DeepStack inputs during replay
- [ROCm] Fuse per-token activation quant into RMSNorm for per-channel quantized attention
- [Model Loader] Harden startup weight-load overlap and expand model coverage
- feat(test): Add VLM memory leak test (Issue #8496)
- [PP] Refactor Async Pipeline Parallelism
- [Roadmap]: SGLang Distributed KVCache System For Agentic Workload
- feat(mooncake): propagate per-request context to store RPC for end-to-end request tracing
- dsv4(npu): support prefill context parallelism with interleave(with layersplit) and zigzag
- [fix] Add PCIe device cross-NUMA node detection to prevent model output corruption
- Docs
- Python not yet supported