Pith

open record

sign in
Browse

arxiv: 2011.10680 · v3 · pith:P2ESR4N6 · submitted 2020-11-20 · cs.CV

HAWQV3: Dyadic Neural Network Quantization

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:P2ESR4N6record.jsonopen to challenge →

classification cs.CV
keywords quantizationintegermixed-precisionhawqv3integer-onlylatencyuniformaccuracy
0
0 comments X
read the original abstract

Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values. This hidden cost limits the latency improvement realized by quantizing Neural Networks. To address this, we present HAWQV3, a novel mixed-precision integer-only quantization framework. The contributions of HAWQV3 are the following: (i) An integer-only inference where the entire computational graph is performed only with integer multiplication, addition, and bit shifting, without any floating point operations or even integer division; (ii) A novel hardware-aware mixed-precision quantization method where the bit-precision is calculated by solving an integer linear programming problem that balances the trade-off between model perturbation and other constraints, e.g., memory footprint and latency; (iii) Direct hardware deployment and open source contribution for 4-bit uniform/mixed-precision quantization in TVM, achieving an average speed up of $1.45\times$ for uniform 4-bit, as compared to uniform 8-bit for ResNet50 on T4 GPUs; and (iv) extensive evaluation of the proposed methods on ResNet18/50 and InceptionV3, for various model compression levels with/without mixed precision. For ResNet50, our INT8 quantization achieves an accuracy of $77.58\%$, which is $2.68\%$ higher than prior integer-only work, and our mixed-precision INT4/8 quantization can reduce INT8 latency by $23\%$ and still achieve $76.73\%$ accuracy. Our framework and the TVM implementation have been open sourced.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures

    cs.AR 2026-06 unverdicted novelty 4.0

    SEADA introduces an analytical framework combining cost models, mapping tools, and entropy-based precision selection to optimize mixed-precision DNNs on multi-precision spatial architectures.

  2. A Hardware-Aware, Per-Layer Methodology for Post-Training Quantization of Large Language Models

    cs.LG 2026-05 unverdicted novelty 4.0

    SOP post-training quantization for LLMs reports lower weight reconstruction error than per-layer FP8 at 1.5 bpw lower cost using per-layer codebook search and hardware-aware formats.