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] [NVIDIA] deepseek_v4: Use DeepGEMM paged-MQA metadata for low-ratio indexers on SM120
- [Perf] [NVIDIA] fp8: Add Triton block-fp8 GEMM configs for RTX PRO 5000
- [Feat] moe: B12x W4A16 E4M3 K/32 route with EP support for ModelOpt mixed checkpoints
- fix(xpu): align FlashAttention fake with fwd outputs
- [Fix] spec: Accept pp_proxy_tensors in FrozenKVMTP and UNO workers
- [CI] [Intel] disaggregation: Run XPU P/D nightly on Mooncake and NIXL
- [Feat] [NVIDIA] speculative: Add DLite decoding for Qwen3.
- [Perf] multimodal: Lazily initialize CUDA VMM feature transport
- [Fix] openai: Sync token usage for streaming gpt-oss /v1/responses
- [Feat] [NPU] numa: Add Ascend NPU NUMA node discovery for automatic NUMA binding
- Docs
- Python not yet supported