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
- [Fix] Coordinate multi-tokenizer controls with broadcast_and_wait
- [RFC] FuseEP Integration for MiniMax-M3 Prefill on Ascend NPU
- [Kernel] Fuse chunk topk transform with row_to_page_table direct inde…
- [diffusion] model: restore folded H3 GGUF patch embedding
- [Mamba] Keep extend-row checkpoint tracking through mixed chunk prefill
- [AMD] Shard DSA prefill indexer rows across attention TP ranks
- [ROCm] Route the MoE routing preamble through AITER's fused entry at validated token counts
- [Multimodal] Cache Qwen2.5-VL video preprocessing by caller ID
- [Tracking] Reduce multimodal frontend overhead
- [Fix] Pack non-contiguous weight tensors into flattened buckets
- Docs
- Python not yet supported