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
- [diffusion] Serve the LLaDA-Image Turbo FP8 checkpoint on one GPU
- [GLM-5.3-Flash] Overlap prefill TP all-reduces across two microbatches
- [KDA] Fix prefill-graph track copies with a bf16 SSM pool
- [Bugfix] Honor Inkling reasoning-off requests
- [GLM-5.3-Flash] Fuse KDA output norm in target verify
- [diffusion] feat: add native Stable Diffusion XL pipeline
- [Docs] Diffusion SP: document --kv-gather-degree instead of the nonexistent --sp-attention-mode
- [Docs] Ascend support matrix: drop ngram match-window flags removed in #21225
- [Docs] Env var reference: drop removed vars, document SGLANG_SWA_EVICTION_INTERVAL
- [Docs] Point references at moved and removed source files
- Docs
- Python not yet supported