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] [AMD] lm_head: Opt-in aiter tgemm for the bf16 lm_head on gfx950
- [Perf] allreduce: enable FlashInfer AllReduce Fusion auto-enable for Kimi-K3
- [Perf] [AMD] mori: pack KV pages for heterogeneous TP
- [Perf] [AMD] mooncake: pack heterogeneous-TP SWA KV pages
- [Doc] docs: Fix stale links to moved and removed repo files
- [Perf] activation: Add a JIT CUDA xIELU kernel for Apertus
- [Feat] [AMD] runtime: Add a master switch for monokernel runtime optimizations
- [Perf] [AMD] spec: Many-block softmax, top-p and chain rejection for ROCm DSpark verify
- [Perf] dspark: Cut the DeepSeek-V4.1 draft and accept launches
- [Doc] cookbook: Add NIM 2.1.3–2.1.5 recipes and evidence
- Docs
- Python not yet supported