HPE puts storage to work on AI’s expensive memory problem

By holding inference state that would otherwise be evicted from GPU memory, HPE's solution achieved up to 20x faster time to first token and 17x higher throughput in tests with NVIDIA H200 GPUs. This approach reduces the need for GPUs to repeatedly recalculate the same context in agentic workflows.

Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The Register did the reporting; read the original for the full story.