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(symm-mem): disable multimem all-gather when the local GPUs have no peer access
- docs: add Halo post-training integration
- [unified-memory] Admit EAGLE/EAGLE3 onto fused draft KV, on mamba-MHA and MLA hosts
- [unified-memory] Admit DFLASH and DSPARK with fused draft KV
- [diffusion] Honor --vae-slicing in the native decoding stage
- fix(moe): preserve negative routing sentinel in EP mapping
- [DSV4.1] Skip invisible SM90 FP4 indexer tiles
- chore: update CI test est_time values
- [DSV4.1] Enable Engram WKV projection sharding
- [NPU] Add startup, checkpoint, chat-template, radix-backend, and HiCache tests
- Docs
- Python not yet supported