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
- [Bugfix] Reserve the symmetric-memory prealloc out of the KV budget
- [RFC] Preserve multimodal identity end to end: precomputed inputs, collision-safe KV reuse, and KV-event parity
- [Feat] hicache: Add opt-in tail-only SWA backups in buffer mode
- [Fix] dsa: Route mixed-chunk batches to the RAGGED top-k transform for bf16-only sparse prefill
- [Bug] DeepSeek-V4.1-Flash on SM120: historical report of NCCL initialization failure with DSPARK
- [Perf] diffusion: convrot_int8 comfy_kitchen issues one GEMM per layer by default
- [Perf] minimax-m3: Cache CPU image preprocessing artifacts
- [Feat][GPU] cosmos3: support gpu preprocess fo v2v
- ADR: releasing decode KV pages after a failed PD transfer
- [Bug] Ordinary API key can trigger remote-instance weight export
- Docs
- Python not yet supported