Trending

Touching the Elephant – TPUs

TPUs vs. GPUs and why Google is positioned to win AI race in the long term

AI Is Writing Its Own Kernels, and They Are 17x Faster

Driving TFEL with RP2040: Offloading the CPU step by step (2021)

Jasmine: A Simple, Performant and Scalable Jax-Based World Modeling Codebase

The State of Machine Learning Frameworks in 2019

A minimal tensor processing unit (TPU), inspired by Google's TPU

Tensor Manipulation Unit (TMU): Reconfigurable, Near-Memory, High-Throughput AI

TPU Deep Dive

Google Metrax Brings Predefined Model Evaluation Metrics to JAX

Recently open-sourced by Google, Metrax is a JAX library providing standardized, performant metrics implementations for classification, regression, NLP, vision, and audio models. By Sergio De Simone

Google has stepped into the picture when it comes to selling TPUs vs GPUs now.

[D] Why TPUs are not as famous as GPUs

[D] What is up with Tensorflow and JAX?

custom Vulkan C++ machine learning library vs TensorFlow [R]

[P] RetinaNet + MobileNetV2 for Edge TPU Deployment

[D] Conceptually/On a Code Basis - Why does Pytorch work with CUDA out of the box, with minimal setup required, but tensorflow would require all sorts of dependencies?

[Project] Detecting Rooftop Solar Panels in Satellite Images Using Mask R-CNN and TensorFlow

[P] I Fine-Tuned a Language Model on CPUs using Nativelink & Bazel

[D] Anyone else using Tensordock cloud GPU and now feeling frustrated?