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"”.
-
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 …
-
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 …
-
Diseño de una plataforma tecnológica de alto rendimiento con procesamiento por gráfica y basada en tecnología de hiperconvergencia para la aplicación de la inteligencia generativa en el desarrollo de sistemas predictivos de información con el entrenamiento de modelos de Inteligencia Artificial (IA)
… en precisión FP16 y 1513 TFLOPS en formato FP8; además, se elevará la velocidad de reloj de los núcleos de cómputo a 1755MHz aprovechando las capacidades del procesamiento en paralelo incorporando la tecnología NVIDIA NVLink; asimismo, se aumentará el número de tokens de la ventana de …