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
- [Spec] perf: fuse draft extend metadata prep
- DSpark support DeepEP & MegaMoE
- test(jit): cover CUDA arch-suffix defaulting
- disaggregation/mori: track true end-to-end KV transfer latency + per-chunk avg bandwidth
- [LoRA] Add clean BF16 SGL LoRA MoE execution slice
- hicache: restore per-tier (L1/L2/L3) KV cache hit metrics
- hicache: restore eviction/load-back bandwidth and byte-level metrics
- [Bug] Fix multi-tokenizer BatchEmbeddingOutput repack dropping fields
- [Bug] sglang with cp=8 metric num_requests_running display is error
- Optimize MXFP4 Marlin repack memory usage
- Docs
- Python not yet supported