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
- [NPU] Support DWDP on Ascend NPU
- [AMD] DSA: disable async copy and retune split-K for sparse-MLA spec-verify on gfx950
- [CPU] add fused_dual_residual_rmsnorm cpu kernel on xeon
- [MLU][CI] Bootstrap MLU runner workflows
- [mem_cache] Size the unified-pool req_to_token row from the shared headroom helper
- [CPU][Diffusion] Add timestep_embedding kernel for CPU
- [Bugfix] Olmo3: size sliding-window layers from the hybrid SWA pool
- [Feature] Exaone4: size sliding-window layers from the hybrid SWA pool
- [multimodal] Stop packing per-image features only to split them again
- [multimodal] Stop each per-item feature shipping the whole packed buffer over IPC
- Docs
- Python not yet supported