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
- [Feat] hicache: Add unified Engram store and support Qwen4-Exp
- [Fix] diffusion/realtime: Reserve generation slots after initialization
- [Refactor] [Apple] MLX: Fix array leak in Metal kernel bindings
- [Doc] [NPU] cookbook: Add Ascend A3 deployment scenarios for DeepSeek-R1 (W4A8)
- [Perf] scheduler/hicache: Replace O(B^2) request and page list scans in ScheduleBatch.filter_batch, BatchResultProcessor, and RankMetadata
- [Feat] [NPU] dspark: Integrate native sampling and verification kernels
- [Doc] cookbook: Fill the Qwen3.8-Flash-Next NVFP4 B200/B300 benchmark cells
- [Feat] [NPU] moe: Add Ascend Ops backend for MoE prefill and decode
- [Perf] [AMD] diffusion: bound MIOpen find for the Conv2d VAE path
- [Feat] [NVIDIA] modelopt: Opt-in block-FP8 dense layers for NVFP4 che…
- Docs
- Python not yet supported