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] model_loader: Fault mmap'd safetensors views in on the CPU on integrated GPUs
- [Fix] dsv4: Keep a coordinated verify rank out of the decoder-tail idle replay
- [Fix] distributed: Probe the TP group's node span on the first multimem all-gather
- [Feat] [AMD] minimax: gfx950 sparse attention, NVFP4 KV and DSpark verify kernels
- [Refactor] attention: Route every FlashAttention call through the selected kernel
- [Fix] FlashInfer: Tune one prefill shape during MoE startup
- [Feat] linear-attn: Bole spec-verify for GDN (drop per-draft SSM snapshots)
- [Refactor] diffusion/bcg: Share graph-pool output management
- [Fix] embedding: Force full recompute when pooling reads inside a cached prefix
- [Fix] [MUSA] fa3: Preserve draft-extend prefix KV attention
- Docs
- Python not yet supported