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
- [Perf] dsa: Route the k-pool indexer top-k through the top-k v2 kernel
- [NPU] Set Ascend env for all build layers and shell sessions
- Support HiCache with KV Cache Sharding
- [OpenAI] Return a real HTTP error for streams rejected before the first chunk
- [diffusion] add bug detection support for minimax-h3 lora_B 2d bug
- [PD] Enable Mooncake decode host receive
- [PD] Fix pd_dcp_gather grid.y overflow and vectorize pack gather to 8-byte lanes
- Add SGLANG_TRTLLM_WORKSPACE_MB env for trtllm_mla workspace sizing
- [AMD] Qwen3.5: pack GDN in_proj_qkvz+ba into one AITER ASM MXFP4 GEMM
- QSA Context Parallel Optimization
- Docs
- Python not yet supported