[MLX] C++ runner for HF LLMs with the off-graph KV cache - #21683

[MLX] C++ runner for HF LLMs with the off-graph KV cache#21683

kiymetakdemir wants to merge 1 commit into

pytorch:mainpytorch/executorch:mainfrom

kiymetakdemir:mlx-offgraph-hf-runnerkiymetakdemir/executorch:mlx-offgraph-hf-runnerCopy head branch name to clipboard