REVIEW 6 cited by
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant over-fitting. Instead, these methods only use the calibration set to set the activations' dynamic ranges. However, such methods always resulted in significant accuracy degradation, when used below 8-bits (except on small datasets). Here we aim to break the 8-bit barrier. To this end, we minimize the quantization errors of each layer separately by optimizing its parameters over the calibration set. We empirically demonstrate that this approach is: (1) much less susceptible to over-fitting than the standard fine-tuning approaches, and can be used even on a very small calibration set; and (2) more powerful than previous methods, which only set the activations' dynamic ranges. Furthermore, we demonstrate how to optimally allocate the bit-widths for each layer, while constraining accuracy degradation or model compression by proposing a novel integer programming formulation. Finally, we suggest model global statistics tuning, to correct biases introduced during quantization. Together, these methods yield state-of-the-art results for both vision and text models. For instance, on ResNet50, we obtain less than 1\% accuracy degradation --- with 4-bit weights and activations in all layers, but the smallest two. We open-sourced our code.
Forward citations
Cited by 6 Pith papers
-
FPTQuant: Function-Preserving Transforms for LLM Quantization
FPTQuant introduces function-preserving transforms that make transformer activations amenable to static 4-bit quantization with minimal inference overhead.
-
A Reconfigurable and Representation-Adaptive ISA-Based Architecture for Efficient DNN Acceleration
A representation-adaptive ML-oriented ISA plus reconfigurable architecture with RNS dynamic precision delivers 5–10 TOPS/W and up to 1.2× efficiency over fixed-point while remaining programmable.
-
MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation
MPQ-DMv2 adds binary residual quantization, temporal relation distillation, and SVD-initialized LoRA to mixed-precision quantization, improving low-bit diffusion model generation quality.
-
Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference
DPQ is a post-training quantization algorithm that stores weights in INT4, computes in FP8, and uses Hessian-based group-aware reordering to keep accuracy near the full-precision model.
-
Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models
Pre-tuning a full-precision model with quantization-error noise and weight averaging before PTQ consistently improves low-bit (2-4 bit) quantized accuracy across CNN architectures and segmentation.
-
Efficient Reasoning on the Edge
LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.
Discussion (0). Sign in to comment.