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
- [Fix] cuda_graph: 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
- [ROCm][AMD] Qwen3.8-Flash-Next gfx950 / MI355X Performance Optimization
- Qwen4-Exp (Qwen3.8-Flash-Next) QSA MTP: draft_tokens > compress ratio and topk > 1 crash late in scheduler init instead of failing arg validation
- [Feat] comfyui: Opt-in native worker batching (Z-Image, FLUX.1)
- [Feat] moe: Allow SiTU on the CuTe DSL NVFP4 MoE (Kimi-K3 W4A16)
- [Feat] score/embedding: Add raw embeddings, score rids, encode input_ids, and schedule-decision logging
- [Fix] benchmark: Compensate cumulative request arrival drift
- [Feature] Could you include the sgl-model-gateway container image alongside each version release?
- Docs
- Python not yet supported