How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training
This paper investigates three different parameterizations of asymmetric uniform quantization for quantization-aware training: (1) scale and offset, (2) minimum and maximum, and (3) beta and gamma. We perform a comprehensive comparative analysis of these parameterizations' influence on quantization-aware training, using both controlled experiments and real-world large language models. Our particular focus is on their changing behavior in response to critical training hyperparameters, bit width and learning rate. Based on our investigation, we propose best practices to stabilize and accelerate quantization-aware training with learnable asymmetric quantization ranges.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Exploring Post-Training Quantization of Protein Language Models
Recent advancements in unsupervised protein language models (ProteinLMs), like ESM-1b and ESM-2, have shown promise in different protein prediction tasks. However, these models face challenges due to their high computati…
Protein Structure PredictionQuantizationLSQ+: Improving low-bit quantization through learnable offsets and better initialization
Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges.…
Image ClassificationQuantizationPioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, p…
DenoisingQuantizationHybrid and Non-Uniform DNN quantization methods using Retro Synthesis data for efficient inference
Existing post-training quantization methods attempt to compensate for the quantization loss by determining the quantized weights and activation ranges with the help of training data. Quantization aware training methods, …
QuantizationAFPQ: Asymmetric Floating Point Quantization for LLMs
Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Altho…
Quantization