October 17, 2023
PyTorch Edge: Enabling On-Device Inference Across Mobile and Edge Devices with ExecuTorch
We are excited to announce ExecuTorch, our all-new solution for enabling on-device inference capabilities across mobile and edge devices with the backing of industry leaders like Arm, Apple, and Qualcomm Innovation Center.
October 17, 2023
Lightning AI Joins the PyTorch Foundation as a Premier Member
The PyTorch Foundation, a neutral home for the deep learning community to collaborate on the open source PyTorch framework and ecosystem, is announcing today that Lightning AI has joined as a premier member.
October 17, 2023
Huawei Joins the PyTorch Foundation as a Premier Member
Today, the PyTorch Foundation, a neutral home for the deep learning community to collaborate on the open source PyTorch framework and ecosystem, announced that Huawei has joined as a premier member.
October 17, 2023
Compiling NumPy code into C++ or CUDA via torch.compile
Quansight engineers have implemented support for tracing through NumPy code via torch.compile in PyTorch 2.1. This feature leverages PyTorch’s compiler to generate efficient fused vectorized code without having to modify your original NumPy code. Even more, it also allows for executing NumPy code on CUDA just by running it through torch.compile under torch.device("cuda")!
October 11, 2023
ML Model Server Resource Saving - Transition From High-Cost GPUs to Intel CPUs and oneAPI powered Software with performance
Reviewers: Yunsang Ju(Naver GplaceAI Leader), Min Jean Cho(Intel), Jing Xu(Intel), Mark Saroufim(Meta)
October 10, 2023
Real-time Audio-visual Speech Recognition
Audio-Visual Speech Recognition (AV-ASR, or AVSR) is the task of transcribing text from audio and visual streams, which has recently attracted a lot of research attention due to its robustness to noise. The vast majority of work to date has focused on developing AV-ASR models for non-streaming recognition; studies on streaming AV-ASR are very limited.
