Note to others reading along: in the last appendix page the OP paper reports DFloat11 reduces tokens/sec by ~2-3x for the Llama-3.1-8b and Qwen-2.5-14b/32b and Mistral-small-24b models (throughput penalty not reported for others).
Using DFloat11, tokens/sec was higher only when compared relative to running inference with some layers offloaded to CPU.
Classic comp sci tradeoff between space and speed, no free lunch, etc.
Using DFloat11, tokens/sec was higher only when compared relative to running inference with some layers offloaded to CPU.
Classic comp sci tradeoff between space and speed, no free lunch, etc.