Search Results for author:
Found 2 papers, 0 papers with code
Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization
Our HP can achieve higher sparsity ratio and is more flexible than other sparsity pattern.
Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices
Specifically, RT3 integrates two-level optimizations: First, it utilizes an efficient BP as the first-step compression for resource-constrained mobile devices; then, RT3 heuristically generates a shrunken search space based on the first level optimization and searches multiple pattern sets with diverse sparsity for PP via reinforcement learning to support lightweight software reconfiguration, which corresponds to available frequency levels of DVFS (i. e., hardware reconfiguration).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
