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
- [XPU] Enable FP8 MoE dispatch across FP8 quantization methods
- [Fix] Protect GDN state pool from SM90 FlashInfer decode padding
- [Bug] PD prefill: early cached-prefix send can transfer KV before the HiCache load-back finishes (stale KV on decode)
- [diffusion] Fix opt-in Wan2.2 progressive mode and one-step transitions
- [Fix] hicache: Key MLA Mamba state per TP rank in the SeaweedFS backend
- [Fix] hicache: Key MLA Mamba state per TP rank in the HF3FS backend
- [SAIL][2/N] Add initial T-HEAD SAIL platform support
- [Fix] Align conv layout when copying between mamba checkpoint pool an…
- [Bug] bench_serving: --request-rate falls further behind schedule with every request, so the achieved rate is below the requested rate
- feat(bench): report goodput and SLO attainment in bench_serving
- Docs
- Python not yet supported