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] RL: Keep routed-expert rows only for MoE layers
- [Feat] sail: support DeepGEMM GEMM/MoE backends [4/N]
- [Perf] diffusion: Fuse LTX video VAE normalization and padding
- [Feat] [NPU] DSV4.1: Support DeepSeek-V4.1 on Ascend A5
- [Feat] Spark2.5: Support Spark2.5 Dspark
- [Feature] Per-node HTTP frontend for data-parallel groups spanning nodes, addressed by global `X-Data-Parallel-Rank`
- [Fix] [Intel] moe: Route dropped slots at weight 0
- [Perf] cosmos3: support nvenc convert image to videos
- [Perf] [NVIDIA] dsv4: avoid CP compressor input reorder with rank-major reads
- [Fix] moe: Correctly route fused shared experts and normalize routed topk in grouped_topk
- Docs
- Python not yet supported