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
- [VLM][MM refactor 1/6] Move multimodal enums to a shared module
- [VLM][MM refactor 2/6] Initialize multimodal processors from a processor config
- [VLM][MM refactor 3/6] Extract a shared media processor mixin
- [VLM][MM refactor 4/6] Add token-space multimodal processing
- [Perf] Fuse BF16 QK normalization and multimodal rotary on Blackwell
- [Performance] GGUF: use MMQ from 2 rows for very large matrices (e.g. lm_head)
- [Feature] Add native SmolLM3 support
- Support smollm3
- [Perf] GGUF: merged linear shards as flat views, no per-forward weight copy
- [Quant] compressed-tensors NVFP4 MoE: add Marlin (W4A16) path
- Docs
- Python not yet supported