vllm.v1.simple_kv_offload ¶
Modules:
-
copy_backend–DMA copy backend for GPU<->CPU block transfers.
-
cuda_mem_ops–Low-level CUDA/HIP memory helpers: pinning and batch DMA transfers.
-
manager–Scheduler-side manager for SimpleCPUOffloadConnector.
-
metadata–Metadata for SimpleCPUOffloadConnector.
-
worker–Worker-side handler for SimpleCPUOffloadConnector.