Question

How does Axelera speed up models?

Hello, is there a detailed document where I can learn about the Axelera chip architecture and how to do the quantization in it?
Thanks

+2

Hi @oguz!

There are a few things you could take a look at that might help with this 😃

There’s some background here on the Axelera AI tech: https://axelera.ai/technology
This blog post about benchmarks has some good info in there:

Is there something specific you’re looking for in terms of quantization operations?

Hi @oguz , also for detailed information about the Metis chip architecture, please have a look at https://ieeexplore.ieee.org/document/10454395.

Sign up