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 GLM-5.3 Flash LoRA projection dimensions
- [Speculative] Capture reusable verification sampling in CUDA graphs
- [MoE] Add H100 unified block-FP8 config for E128/N768
- fix: honor UE8M0 activation scales in block-FP8 CUTLASS
- [CI] Retry transient GitHub API errors in wait-for-jobs
- [MemCache] Select Rust tree components with named factories
- [CustomAllReduceV2] Add 2shot_push all-reduce and retune SM100 TP4/TP8
- [Spec] DSPARK read_accept: return copies, not views of buffers the next verify replay rewrites (fixes #42465)
- [Perf] Plan FlashInfer paged prefill from CPU metadata
- [XPU] Let Inkling use the Mamba extra_buffer strategy on XPU
- Docs
- Python not yet supported