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
- [Intel][XPU] Add pyxccl: direct Intel oneCCL communicator for XPU
- [XPU] Enable symmetric-memory one-shot all-reduce
- [NPU][CI] Disable DeepSeek-V2-Lite-W8A8 tests in the PR pipeline
- feat(jit): support native MUSA compilation
- [Bugfix] Keep rope_theta when --json-model-override-args overrides rope_scaling
- [GLM-5.3-Flash] Fuse the FFN mHC post into the next layer's attention pre
- deepep_v2: accept the situ activation in the DeepGEMM pre-permute
- test(npu): add e2e test for --enable-int8-mamba-checkpoint reuse
- [AMD][V4.1] Optimize FP4 indexer with shared K loads and candidate-only scoring
- [Fix][Spec] Release draft embed/lm_head copies before KV pool sizing
- Docs
- Python not yet supported