Post-transformer inference: 224× compression of Llama-70B with improved accuracy
https://zenodo.org/records/17873275
#HackerNews #PostTransformer #Inference #Llama70B #Compression #ImprovedAccuracy
Vsora Jotunn-8 5nm European inference chip
https://vsora.com/products/jotunn-8/
#HackerNews #Vsora #Jotunn-8 #5nm #European #inference #chip #technology #innovation #AI #hardware #semiconductor