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 macOS linking for rust server
- [Spec] DFlash2: support tied lm_head without vocab metadata (Gemma 4)
- [DSV4] perf: shard the MHC prenorm prewarm across co-located ranks
- [DSV4] perf: read only the shards holding the DSPARK draft head
- fix(npu): preserve Ascend TP routing weight precision
- [kernel] add fused silu and mul quant fp8
- Update memfabric-zbal version to 1.1.3
- [Perf] Cache DeepSeek expert-name matching across weight updates
- [sglang-miles] Cache DeepSeek expert-name matching across weight updates
- [AMD] Use Triton prefill attention via Aiter backend
- Docs
- Python not yet supported