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
- MSCCLPP EP
- Supports host RDMA communication protocol in PD disaggregation scenarios
- Feature/npu mm global cache npu memcache
- [Bug] MiMo-V2 processor fails to register when optional TorchCodec is unavailable
- [Bug] MiMo-V2 selects the FP8 MoE runner for packed MXFP4 experts on SM100
- [AMD] [Kimi-K3] Fix bf16 SSM decode under HIP graphs
- [KDA] Fix ptx_kda prefill NaN without a gate lower bound and workspace growth
- [AMD] fix: enable MiMo V2.6 MXFP4 on ROCm
- Main a5 pd
- [Observability] Propagate entry received_time through /v1/score and /v1/responses
- Docs
- Python not yet supported