{"library":"sgl-kernel","type":"library","category":null,"description":"sgl-kernel is the core kernel library for SGLang, providing high-performance GPU-accelerated operations for LLM inference, including optimized attention, MoE routing, and CUDA graph execution. It is primarily used as a dependency of the main `sglang` library, which is currently at version `0.5.10.post1` and sees frequent updates.","language":"en","status":"active","version":"0.5.10.post1","tags":["llm","inference","gpu","cuda","attention","pytorch","moe"],"last_verified":"Wed May 27","install":[{"cmd":"pip install sglang","imports":["from sgl_kernel.cuda_helper import get_memory_info"]},{"cmd":"pip install sgl-kernel","imports":[]}],"homepage":"https://sgl-project.github.io","github":null,"docs":null,"changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":35,"avg_install_s":15.3,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/sgl-kernel/compatibility"}}