PyTorch

5 updates on PyTorch.

  1. Meta's MobileLLM-Flash goes shallow and wide for 1.8 times faster prefill

    Meta designed 350M, 650M and 1.4B models by measuring latency on a Galaxy S25, reversing the deep-and-thin rule of the first MobileLLM.

  2. ExecuTorch 1.0 reaches general availability for on-device PyTorch models

    The PyTorch edge runtime promotes Core ML, Qualcomm Hexagon, Arm Ethos-U, Vulkan and XNNPACK backends to production status.

  3. Apple team finds H100 last on tokens per dollar for models up to 2B

    Seven Apple authors measured tokens per dollar for LLaMA-style models from 100M to 2B and found H100s last at every size, behind cheaper A100s.

  4. torchchat runs Llama 3 8B on a Galaxy S23 and iPhone at more than 8 tok/s

    PyTorch's demonstration codebase exports Llama models to ExecuTorch and ships iOS and Android sample apps for running them on a phone.

  5. ExecuTorch alpha runs Llama 2 7B on iPhone 15 Pro and Galaxy phones

    PyTorch's edge runtime brought 4-bit Llama 2 7B to iPhone and Galaxy handsets, added early Llama 3 8B support and leaned on Apple, Arm and Qualcomm.