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: add exist_ok=True to qwen3_asr AutoConfig.register
- Fix mamba conv state dtype defaulting to bfloat16 for FP16 hybrid linear-attention models
- [Feature] Enable a16w4 MXFP4 MoE on the aiter fp4_bf16 FlyDSL path
- Reduce tensor-parallel logits communication with a rank-0 gather
- Fix custom all-reduce deadlock when one communicator is issued from two CUDA streams
- [LoRA] Fuse absorbed-MLA kv_b_proj LoRA correction (4 kernels → 2)
- [PD] Enable mooncake TCP connection pool by default for mooncake_tcp backend
- Fix UE8M0 scale rounding for DeepGEMM
- Revert dynamo-compiling guard on flashinfer RMSNorm
- fix: balance automatic NUMA binding across affinity nodes
- Docs
- Python not yet supported