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] kimi-k3: Run Quark MXFP4 shared experts in BF16 on the merged MoE front
- [WIP] Adds the SGLang kernel and runtime primitives required by UBTree
- [Feat] [NPU] qwen-image: Adapt Qwen-Image 2.1 on Ascend
- [ROCm][DSA] Add opt-in shape-aware prefill backend selection
- [diffusion][AMD] kernels: give mul_rn_f32 a ROCm path and re-enable the MiniMax-H3 VAE fused norms on ROCm
- [Fix] GraniteMoE: pass RoutingMethodType to FusedMoE for flashinfer_trtllm
- [Fix] [CPU] runtime: Defer optional AOT imports for torch_native serving
- [Doc] examples: Demonstrate CPU prefix reuse with full-response metrics
- [UMBP] Support MiniMax-M3 sparse KV in the direct external linker
- [model-gateway] Send worker API key during initial HTTP health check
- Docs
- Python not yet supported