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
- docs(cookbook): GLM-5.2 single-node benchmarks
- [DO NOT MERGE] Test Mooncake DMA-BUF wheels in CUDA stages
- [Rust server] Support parallel sampling (n > 1) on native /generate
- [LoRA] Accumulate torch-native graph expand GEMM into output
- [Sampling] Add `SGLANG_RENORM_DETERMINISTIC` for bit-identical top-p / top-k renorm
- fix(step3p7): support batched multimodal image features
- [weight_cache] Add `status` request and CLI for daemon monitoring
- [Roadmap] SGLang dLLM Serving
- [RL] Stream LoRA adapter weights through the weight-update session
- [Bug] Decode Throughput Inconsistency Between bench_serving and Engine Logs
- Docs
- Python not yet supported