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
- [NPU] Set Qwen3.6 accuracy cases to greedy decoding and tune retries
- [NPU][MiMo] Fold attention_value_scale into o_proj weights
- fix(inkling): return 400 instead of 500 for unfetchable/undecodable multimodal input
- [NPU][LoRA] Update for follow-up with changes in sgl-kernel-npu
- [Disagg] Support heterogeneous TP for hybrid SWA KV transfer
- Support kv cache sharding for DSA indexer
- Support kv cache sharding for MTP
- [Perf] Optimize SM90 DSV4.1 static verification indexing
- [Bug] Triton kernel load_binary fails with "operation not permitted" during decode CUDA graph replay (QSA graph_metadata) on GB10/SM121, cascades into GPU-memory exhaustion and a full driver lockup requiring hard reboot
- [Bug][Spec] Keep adaptive target graph construction outside draft contexts
- Docs
- Python not yet supported