Attention Quantization for Tabular Foundation Models
FP8 quantization of attention queries, keys, and values speeds tabular foundation model inference up to 1.7x with no accuracy loss.
1 stories, newest first · one card per story
FP8 quantization of attention queries, keys, and values speeds tabular foundation model inference up to 1.7x with no accuracy loss.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views