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
- Interleave decode passes between mixed prefills
- [Spec] perf: Fuse draft-extend topk=1 postprocess
- Fix structural tag grammar validation
- fix(hicache): make device eviction sync-free
- [RFC] An NPU-Native, Sparsity-Driven KV Offloading SubSystem for Efficient LLM Decoding
- disaggregation/mooncake: time out KV receivers stuck in Transferring
- [Inkling] Bound audio embedding memory
- [Fix] Apply gemm1_clamp_limit in silu-mul-quant kernels without gemm1_alpha
- [Fix] Normalize --speculative-algorithm NONE to None during arg resolution
- [Bug] DWDP unconditionally imports cuda.bindings → ModuleNotFoundError: No module named 'cuda' on non-CUDA platforms (XPU/CPU) during ModelRunner init
- Docs
- Python not yet supported