Accelerating ViT Inference on FPGA through Static and Dynamic Pruning
This work addresses the problem of deploying ViTs in real-world applications by improving efficiency for edge computing scenarios, though it is incremental as it builds on existing pruning techniques.
The paper tackles the high computational complexity of Vision Transformers (ViTs) by proposing an algorithm-hardware codesign that combines static weight pruning and dynamic token pruning, resulting in accelerated inference on FPGA with reduced model size and maintained accuracy.
Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight and token pruning are two well-known methods for reducing complexity: weight pruning reduces the model size and associated computational demands, while token pruning further dynamically reduces the computation based on the input. Combining these two techniques should significantly reduce computation complexity and model size; however, naively integrating them results in irregular computation patterns, leading to significant accuracy drops and difficulties in hardware acceleration. Addressing the above challenges, we propose a comprehensive algorithm-hardware codesign for accelerating ViT on FPGA through simultaneous pruning -combining static weight pruning and dynamic token pruning. For algorithm design, we systematically combine a hardware-aware structured block-pruning method for pruning model parameters and a dynamic token pruning method for removing unimportant token vectors. Moreover, we design a novel training algorithm to recover the model's accuracy. For hardware design, we develop a novel hardware accelerator for executing the pruned model. The proposed hardware design employs multi-level parallelism with load balancing strategy to efficiently deal with the irregular computation pattern led by the two pruning approaches. Moreover, we develop an efficient hardware mechanism for efficiently executing the on-the-fly token pruning.