KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU
KVMem is presented, a KV-context virtualization system that preserves overflowed workspace history as paged KV state across GPU memory, host memory, and NVMe, and provides a practical path toward long-running agents whose workspaces can grow beyond that window.
Di Chai, Le-Ye Wang, Ze-Shen Su et al.
· 1 citation