One-Shot Model for Mixed-Precision Quantization
Neural network quantization is a popular approach for model compression. Modern hardware supports quantization in mixed-precision mode, which allows for greater compression rates but adds the challenging task of searching for the optimal bit width. The majority of existing searchers find a single mixed-precision architecture. To select an architecture that is suitable in terms of performance and resource consumption, one has to restart searching multiple times. We focus on a specific class of methods that find tensor bit width using gradient-based optimization. First, we theoretically derive several methods that were empirically proposed earlier. Second, we present a novel One-Shot method that finds a diverse set of Pareto-front architectures in O(1) time. For large models, the proposed method is 5 times more efficient than existing methods. We verify the method on two classification and super-resolution models and show above 0.93 correlation score between the predicted and actual model performance. The Pareto-front architecture selection is straightforward and takes only 20 to 40 supernet evaluations, which is the new state-of-the-art result to the best of our knowledge.
Code (0)
등록된 구현이 없습니다.
Tasks
modelModel CompressionQuantizationSuper-ResolutionSimilar Papers 제목 키워드 기반
FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search
Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent har…
QuantizationZeroQ: A Novel Zero Shot Quantization Framework
Quantization is a promising approach for reducing the inference time and memory footprint of neural networks. However, most existing quantization methods require access to the original training dataset for retraining dur…
Data Free QuantizationModel CompressionNeural Network CompressionQuantizationMixed-Precision Quantization for Language Models: Techniques and Prospects
The rapid scaling of language models (LMs) has resulted in unprecedented computational, memory, and energy requirements, making their training and deployment increasingly unsustainable. Quantization has emerged as an ess…
APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models
Large Language Models (LLMs) have greatly advanced the natural language processing paradigm. However, the high computational load and huge model sizes pose a grand challenge for deployment on edge devices. To this end, w…
QuantizationNearly Lossless Adaptive Bit Switching
Model quantization is widely applied for compressing and accelerating deep neural networks (DNNs). However, conventional Quantization-Aware Training (QAT) focuses on training DNNs with uniform bit-width. The bit-width se…
Quantization