Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 3 of 3 for “"FP8"”.

  1. Secure and private machine learning in hardware

    … for high throughput 8-bit floating point (FP8) provided by modern GPUs. Directly training models using FP8 is challenging due to the extremely narrow range of this datatype. We propose EMPATIC, where we cluster the training data so that groups of similar inputs are run contiguously. We then …

    toronto-retro Repository record for Secure and private machine learning in hardware (opens in a new tab)

  2. Comparing the Performance of Small Word-Size Floating-Point Numerics to Fixed-Point Numerics in Neural Networks

    … reduced-precision floating-point formats (FP8, FP12, FP16) for dynamic, layer-wise quantization during training. APT monitors per-layer Quantization Error Measurement (QEM) to guide precision adjustments and incorporates a novel bit-shuffling mechanism to reallocate bits between exponent …

    gatech Repository record for Comparing the Performance of Small Word-Size Floating-Point Numerics to Fixed-Point Numerics in Neural Networks (opens in a new tab)