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: preserve streamed Harmony answer prefixes
- Enable FlashInfer decode attention access for NVFP4 KV cache and fix Gemma4 text config
- [AMD][DI][CI] mi355x spur: choose RDMA devices per node, by rail
- [Spec] Support --speculative-token-map with a vocab-sharded target lm_head (TP>1)
- [Perf] sm_121 (GB10 / DGX Spark) skinny BF16 GEMM for decode projections and lm_head
- feat(model-loader): reuse model-owned MTP rules for shard selection
- [Feature] Support Aleph-Alpha/Kolibri-1
- [Performance] Cake NVFP4 warp-decode regresses TPOT on Qwen3-30B-A3B (GB200 TP1)
- [diffusion] map the merged LoRA cache read-only
- [2/N][DSv41] Integrate DeepGEMM MegaGate routing
- Docs
- Python not yet supported