conftrace_

memory-bound computation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

dynamic quantization (1) large language model (1) arithmetic operation (1) on-device learning (1) transformer training (1) low-precision training (1) memory optimization (1) efficient training (1)

Papers

Dynamic Stashing Quantization for Efficient Transformer Training EMNLP 2023