Scaleway Ampere servers promise AI smarts without breaking the bank

Ampere Computing and French cloud operator Scaleway are pushing Arm-based servers as a more cost-efficient way of operating AI-based services, especially when it comes to inferencing. At the ai-PULSE conference in Paris, the two companies announced availability of cost-optimized COP-Arm instances operated by Scaleway using …

[elsergiovolador]

Bank

Imagine if every time you run your PyTorch script, a bank somewhere in the world would break...

Such a lovely idea.

[druck]

Arse backwards comparison

Wittich claimed that running OpenAI's generative speech recognition model, Whisper, on Ampere's 128-core Altra Max processor consumes 3.6 times less power per inference than operating the same on an Nvidia A10 Tensor Core GPU.

Again with this arse backwards style of comparisons, is part of the hideous Americanization of this once great site?

It should be; an Nvidia A10 Tensor Core GPU consumes 3.6 times more power per inference than Ampere's 128-core Altra Max processor.