One strategy to solve the memory bottleneck is to store the LLM on flash memory and load it into RAM incrementally for inference tasks. While flash memory is more abundant on devices than DRAM, it is slower by at least an order of magnitude.
One strategy to solve the memory bottleneck is to store the LLM on flash memory and load it into RAM incrementally for inference tasks. While flash memory is more abundant on devices than DRAM, it is slower by at least an order of magnitude.