Add measured Snapdragon NPU / GPU section (Galaxy S26)

Card: correct the GPU node counts — the previous figures added the XNNPACK fallback partition to the GPU delegate partition

Card: add a measured Performance table (Pixel 8a, benchmark_model GPU+CPU), naming the runtime for each row

Upload README.md with huggingface_hub

Upload movinet_a0_stream.tflite with huggingface_hub

Upload hero.png with huggingface_hub

Upload README.md with huggingface_hub

initial commit