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
- [Feat] [AMD] torch-profiler: Enable torch.profiler GPU tracing on torch 2.12 / ROCm 10.1
- support cp and bcg in GLM5.3-Flash
- [Perf] [AMD] kimi-k3: Run shared-expert down GEMM through Aiter
- [Fix] Require admin API key for flush_cache and LoRA endpoints
- [Fix] Reset global graph pool and allocator cache on graph cleanup and recapture
- [Perf] [AMD] kimi-k3: Fuse radix route with MXFP4 quant on the prequant path
- [Perf] [NVIDIA] dsa: Shard k-pool prefill rows across TP
- [Feat] simulator: Add baseline collection and ML latency predictor training tools
- [AMD][Qwen3.8]Enable fused GDN packing for ratio-3 heads
- [ROCm][AMD] Qwen3.8-Flash-Next gfx950 / MI355X Performance Optimization
- Docs
- Python not yet supported