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
- [DO NOT MERGE][Test] Tighten the DCP HiCache KL threshold to 0.005
- [Triton] Apply fused vision rotary pos embedding to Qwen2.5-VL: up to…
- Add startup self-benchmarking for ForwardPassMetrics
- [CPU] Support speculative decoding for hybrid GDN models
- refactor(attn): deprecate use_bound parameter on _compute_forward_metadata
- feat(load-reporter): add push-based engine load reporting
- [AMD] Fuse quantized in_proj layers in Qwen3.5
- [diffusion] feat: TeaCache coefficient calibration
- [DLLM] Add fused Triton post-process kernel with on-device fallback
- Enable to test bench_one_batch with image inputs for multimodal
- Docs
- Python not yet supported