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] [NVIDIA] kimi-k3: Low-latency SM107 decode path
- [Feat] model: Add Flint (RecursiveSI/flint) support
- [Fix] [NPU] tests: Apply MMLU thresholds in the DeepEP accuracy tests
- [Feat] pd: Defer single-layer NEXTN draft prefill to decode workers
- [Fix] diffusion: float32 Plucker rays for bf16 camera poses
- [Fix] trtllm-moe: Add explicit workspace to reduce autotuner memory
- [KVCR 1/5] Share rank-local endpoint contracts
- [Feat] hicache: Add host-staged KVCR L3 storage
- [KVCR 4/5] Add request-scoped linker hooks and owned inventory
- [KVCR 3/5] Add opt-in HiCache delivery and placement controls
- Docs
- Python not yet supported