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
- Question: content-based LoRA adapter selection (routing from the query, not the request)
- [Bugfix] Fix Mamba allocation crash in unified memory during radix-cache handoff
- [Bug][Ascend NPU] MTP (NEXTN) crashes on glm-ocr
- [Bug] pause_generation(mode="retract") does not fully release RadixCache KV
- Fix(DSpark): sync device before CUDA graph capture to avoid JIT race
- [fix] Correct metric names in example Grafana dashboard (sglang_* -> sglang:*)
- [docs] Document the gateway /engine_metrics aggregation endpoint
- chore: bump sglang-kernel version to 0.4.6
- perf: Remove redundant D2D copy in layer-split broadcast
- [PD] Charge each state component its own item length in the KV transfer metric
- Docs
- Python not yet supported