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
- feat(metrics): count waiting-queue request rejections
- [Diffusion][LoRA] Rework adapters and implement LoKr adapter
- [AMD] Perf Kimi-K3 low concurrency optimizations
- Keep the DeepSeek router GEMM in fp32 under deterministic inference
- [DSv4] TRTLLM Attention: Accuracy + Perf Improvements
- [Feature] [RFC] [HiCache] Out-of-process HiCache data plane with device-memory IPC
- Fix/encdec decode paged alloc row offset
- [sgl-router] Enable broader Dynamo rendering and token forwarding
- [Feature] Add KV cache usage prometheus metrics
- Bug Fix: Inconsistent Return Values in MiniCPMV Class
- Docs
- Python not yet supported