Midjourney says their research was set back by a year by using TPU, regrets not sticking purely with nvidia
Summary
Midjourney stated that using Google TPUs set their research back by a year, expressing regret for not sticking exclusively with Nvidia hardware.
Similar Articles
@JeffDean: My @Google colleagues @NormJouppi, Sridhar Lakshmanamurthy, Cliff Young, and David Patterson recently wrote a paper tha…
Google researchers published a paper summarizing the evolution of TPU supercomputers from TPU v2 to Ironwood, detailing architectural stability, scale, resilience, power efficiency, and a 3600x performance increase over eight years.
Google Is Using Nvidia's Playbook to Build a Rival AI Chip Business (11 minute read)
Google is adopting Nvidia's strategy to build a competitive AI chip business, renting TPU computing power to Anthropic and boosting inference performance to rival Nvidia's dominance.
Here’s how our TPUs power increasingly demanding AI workloads.
Google explains how its custom Tensor Processing Units (TPUs) are designed to handle massive AI workloads, highlighting the latest generation's ability to process 121 exaflops of compute power.
Our eighth generation TPUs: two chips for the agentic era
Google unveils 8th-gen TPUs: TPU 8t for training and TPU 8i for inference, purpose-built for power-efficient, large-scale AI agent workloads and arriving later this year.
@tbpn: The CUDA moat is real, but probably not for long, says CEO of AI infrastructure platform Modal @bernhardsson. He says h…
The CEO of AI infrastructure platform Modal argues that while CUDA currently enjoys a strong moat, it will erode over 2-3 years as software improves to allow running CUDA code on alternative accelerators like TPUs.