model quantization and pruning

femtoAI is a full-stack AI silicon and compression platform company that turns patented neural-network sparsity into real savings for enterprises. Founded in 2018 by researchers from the Brains in Silicon Lab at Stanford University and headquartered in Silicon Valley, it delivers low-latency, 10X lower power draw and 10X smaller memory footprint for edge AI devices.

Read more

AI accelerator designcompiler developmentneural network sparsity and model compressionperformance simulationsoftware and hardware co-design