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
- [HiCache] Credit the hugetlb pool in the host-memory preflight
- [Qwen3.8-Flash-Next] Streamline QSA prefill selection
- [Bug] OTel tracing loses Scheduler spans when using --tokenizer-worker-num>1
- Precompile GLM vision kernels before KV allocation to avoid first-image OOMs
- fix: wait for HiCache load-back before hybrid MLA KV reads
- [MLX] Kill already-orphaned MLX workers instead of watching PID 1
- fix(compressed-tensors): refuse a quantized embedding instead of igno…
- [observability] Collect avg_request_queue_latency Prometheus metric
- [Fix] Normalize MiniCPM Lightning output across TP ranks
- [Kernel] Fix the row stride passed by the InfLLM-v2 pooling wrapper
- Docs
- Python not yet supported