{"library":"mooncake-transfer-engine","type":"library","category":null,"description":"Mooncake Transfer Engine is a Python binding (using pybind11) for the core data transfer component of the Mooncake project. Mooncake itself is a KVCache-centric disaggregated architecture designed to optimize Large Language Model (LLM) inference. The Transfer Engine provides a high-performance, unified interface for batched data movement across various storage devices and network links, supporting protocols like TCP, RDMA, CXL/shared-memory, and NVMe over Fabric. It is actively maintained with frequent updates and integrations into LLM serving frameworks like SGLang and vLLM.","language":"python","status":"active","version":"0.3.10.post1","tags":["AI/ML","LLM","distributed systems","high-performance computing","RDMA","data transfer","GPU","kv-cache","inference acceleration"],"install":[{"cmd":"pip install mooncake-transfer-engine","imports":["from mooncake_transfer_engine.libs import TransferEngine"]},{"cmd":"pip install mooncake-transfer-engine-non-cuda","imports":[]}],"homepage":null,"github":"https://github.com/kvcache-ai/Mooncake","docs":"https://github.com/kvcache-ai/Mooncake/tree/main/doc","changelog":null,"pypi":"https://pypi.org/project/mooncake-transfer-engine/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":8.3,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/mooncake-transfer-engine/compatibility"},"provenance":{"verified_status":"import_fail","verified_at":"Fri Jul 03","last_verified":"Fri Jul 03","next_check":"Fri Jul 10","install_tag":null}}