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
- [AMD] Add opt-in AITER ASM FP4 GEMM for Quark dense linear
- [feat] On-demand row broadcast for layer-split DSA KV cache
- Add reproducible global-workload MoE TP/EP benchmarks for Ascend
- [Feature] [KV events] Include the removal reason in `BlockRemoved`
- [HiCache] Add staged write-back for the page-unified KV cache layout
- [NPU][MoE] Integrate MiniMax-M3 FuseEP normal-mode prefill path and validation
- [Docs] Add a KV cache events page
- [Fix] Match OpenAI tool schema field order in `Function`
- Remove defensive getattr on always-present fields
- [AMD][CI] Update references for consolidated workflows
- Docs
- Python not yet supported