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] kimi-k3.1: Unroll the SP tail's NVLS collectives and gather routed inputs in one launch
- [Fix] diffusion: Bound VRAM during resident FP8 weight loading
- [Fix] http_server: Hold the HTTP port across the model load
- [Fix] realtime: Preserve omitted transcription settings in partial updates
- [Fix] minimax-h3: preserve per-layer AdaLN parameters with Cache-DiT
- [Perf] [NVIDIA] minimax-h3: add prepared Sage QKV and fused CAKE glue
- [Chore] logits_processor: Remove the shadowed lm-head quant-method helpers
- [Chore] diffusion: Fix wrong and stale comments and docstrings in runtime
- [Refactor] diffusion: Remove dead code in entrypoints, managers and server args
- [Refactor] diffusion: Remove dead code in layers, quantization and runtime utils
- Docs
- Python not yet supported