Papers › HAQ: Hardware-Aware Automated Quantization with Mixed Precision

HAQ: Hardware-Aware Automated Quantization with Mixed Precision

21 Nov 2018CVPR 2019 6arXiv:1811.08886archive 2025-07-28

Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency, which raises a great challenge to find the optimal bitwidth for each layer: it requires domain experts to explore the vast design space trading off among accuracy, latency, energy, and model size, which is both time-consuming and sub-optimal. Conventional quantization algorithm ignores the different hardware architectures and quantizes all the layers in a uniform way. In this paper, we introduce the Hardware-Aware Automated Quantization (HAQ) framework which leverages the reinforcement learning to automatically determine the quantization policy, and we take the hardware accelerator's feedback in the design loop. Rather than relying on proxy signals such as FLOPs and model size, we employ a hardware simulator to generate direct feedback signals (latency and energy) to the RL agent. Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures. Our framework effectively reduced the latency by 1.4-1.95x and the energy consumption by 1.9x with negligible loss of accuracy compared with the fixed bitwidth (8 bits) quantization. Our framework reveals that the optimal policies on different hardware architectures (i.e., edge and cloud architectures) under different resource constraints (i.e., latency, energy and model size) are drastically different. We interpreted the implication of different quantization policies, which offer insights for both neural network architecture design and hardware architecture design.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

AhmadQasim/proxylessnas-dense mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (arXiv:1812.00332; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
MIT-HAN-LAB/ProxylessNAS mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (arXiv:1812.00332; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
ZTao-z/ProxylessNAS mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (arXiv:1812.00332; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
ito-rafael/once-for-all-2 mentioned on GitHubpytorchMITSyntology: not harvested report
mit-han-lab/ProxylessNAS mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (arXiv:1812.00332; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
mit-han-lab/amc mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AMC: AutoML for Model Compression and Acceleration on Mobile Devices (arXiv:1802.03494; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mit-han-lab/once-for-all mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Once-for-All: Train One Network and Specialize it for Efficient Deployment (arXiv:1908.09791; that paper's own run record: 24 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 1 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
newwhitecheng/compress-all-nn mentioned on GitHubtfSyntology: not harvested report
seulkiyeom/once-for-all mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Once-for-All: Train One Network and Specialize it for Efficient Deployment (arXiv:1908.09791; that paper's own run record: 24 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 1 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
songhan/DSD mentioned on GitHubpytorchBSD-2-ClauseSyntology: not harvested report
songhan/SqueezeNet-Residual mentioned on GitHubBSD-2-ClauseSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

QuantizationReinforcement Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections