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
- [Bug] Marlin atomicAdd K-slice reduction is always on for n < 2048, k >= 2048 (dead `if not True:` guard) and is not disabled by --enable-deterministic-inference
- M3 perf
- [Fix] Keep flashinfer MXFP4 permute-index cache on host
- [Fix] Apply --dist-timeout to CPU (gloo) process groups
- [feat] update_weights_from_disk: model_loader_extra_config + rebuild_model
- Cosmos Dreams and Cosmos Multiview
- [diffusion] rocm: fuse BF16 FLUX.1 LayerNorm modulation on gfx90a
- [weight_cache] Add Prometheus `/metrics` endpoint to the daemon
- [feat] Remove wall-clock deadlines from scheduler control-plane comms
- [Fix] Buffer GLM streaming tool arguments until complete
- Docs
- Python not yet supported