mooncake-transfer-engine-cuda13
A KVCache-centric Disaggregated Architecture for large-scale LLM inference and training. (CUDA 13 version)
pip install mooncake-transfer-engine-cuda13 A KVCache-centric Disaggregated Architecture for large-scale LLM inference and training. (CUDA 13 version)
pip install mooncake-transfer-engine-cuda13