Open access
Aug 2026
FP8 Inference in Genomic Foundation Models: Theoretical vs. Realized Speedups on GenomeOcean
FP8 largely preserves biological fidelity across the evaluated scales and inference regimes, while reducing GPU memory footprint at 4B scale and improving energy efficiency during autoregressive generation, however, realized throughput gains remain substantially below FP8’s theoretical 2× hardware ceiling.
Mutian Yu, Robert Egan, Feng-Chen Liu et al.
· bioRxiv · 0 citations