How do you offload the KV cache to CPU or NVMe, and when is it worth the bandwidth hit?
GPU memory runs out well before you run out of conversations to cache. Offloading KV to CPU or NVMe buys capacity, but the interconnect can turn into the new bottleneck. Here is the bandwidth math.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
GPU memory runs out well before you run out of conversations to cache. Offloading KV to CPU or NVMe buys capacity, but the interconnect can turn into the new bottleneck. Here is the bandwidth math.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
