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
- [Perf] MiniMax-H3: fused indexed modulation for FP32 AdaLN tables
- [Bug] Profiler filename components escape output_dir
- [Fix] watermark: Append accepted tokens to history on fused EAGLE verify
- [Feat] watermark: Add DSPARK speculative decoding support
- [Bug] deepep_v2 crashes at startup on a cold DeepGEMM cache: rank-0-only precompile exceeds ElasticBuffer's 100 s GPU timeout
- Breakable prefill CUDA graph backend trips torch CachingHostAllocator assert (`use_count > 0`) when graphs are re-captured after destruction
- [Bug] Fix peak concurrency accounting in bench_serving metrics
- [Feat] models: Ling-3.1-flash day-0 support, Hopper decode opts, prefill overlap, Ling3 fixes
- [Doc] cookbook: GB300 full-set accuracy and tool follow-up output for Ling-3.1-flash
- [Fix] [AMD] kda: Reject match_cutedsl_decode on ROCm and skip its parity tests
- Docs
- Python not yet supported