Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression

• URL: http://arxiv.org/abs/2604.04988v1
• Date: Sun, 05 Apr 2026 06:13:47 GMT
• Title: Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression
• Abstract summary: Motivated by this gap between compression and acceleration, we study a practical, ordered pipeline that targets measured latency.<n>We combine three widely used techniques: unstructured pruning, quantization-aware training (QAT), and knowledge distillation (KD)<n>Across all settings, the ordered pipeline achieves a stronger accuracy-size-latency frontier than any single technique alone.
• Score: 4.049313299965171
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular, unstructured sparsity can reduce model storage while failing to accelerate (and sometimes slightly slowing down) standard CPU execution due to irregular memory access and sparse kernel overhead. Motivated by this gap between compression and acceleration, we study a practical, ordered pipeline that targets measured latency by combining three widely used techniques: unstructured pruning, INT8 quantization-aware training (QAT), and knowledge distillation (KD). Empirically, INT8 QAT provides the dominant runtime benefit, while pruning mainly acts as a capacity-reduction pre-conditioner that improves the robustness of subsequent low-precision optimization; KD, applied last, recovers accuracy within the already constrained sparse INT8 regime without changing the deployment form. We evaluate on CIFAR-10/100 using three backbones (ResNet-18, WRN-28-10, and VGG-16-BN). Across all settings, the ordered pipeline achieves a stronger accuracy-size-latency frontier than any single technique alone, reaching 0.99-1.42 ms CPU latency with competitive accuracy and compact checkpoints. Controlled ordering ablations with a fixed 20/40/40 epoch allocation further confirm that stage order is consequential, with the proposed ordering generally performing best among the tested permutations. Overall, our results provide a simple guideline for edge deployment: evaluate compression choices in the joint accuracy-size-latency space using measured runtime, rather than proxy metrics alone.

Related papers

• CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration [67.17709877327232]
  Cate KV is a hybrid KV cache method that retains only critical token information for consistent heads.<n>Cate KV reduces memory usage by up to $2.72times$ and accelerates decoding by $2.18times$ in single-sample inputs.
  arXiv  Detail & Related papers  (2026-08-31T06:02:37Z)
• Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMs [50.677556944160216]
  MoEXBench is a systematic benchmark for evaluating composable MoE compression as an end-to-end deployment workflow.<n>It measures composable-compression quality, workload and architecture, pruning/quantization/KV cache sensitivity, and deployment efficiency on commodity hardware.
  arXiv  Detail & Related papers  (2026-08-22T00:01:18Z)
• ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning [58.54940026861599]
  textscChunkFT is a memory-efficient fine-tuning framework.<n>textscChunkFT enables gradient computation for arbitrary sub-tensors without modifying the network architecture.<n>textscChunkFT consistently outperforms existing memory-efficient baselines.
  arXiv  Detail & Related papers  (2026-05-20T13:44:44Z)
• Runtime-Certified Bounded-Error Quantized Attention [0.0]
  We present a tiered KV cache architecture that enables runtime-certified attention.<n>A two-term error decomposition yields per-head, per-step bounds on (i) attention distribution distortion from key quantization and (ii) value reconstruction error.<n>Across PG-19, NIAH, and RULER benchmarks, the system matches dense FP16 KV quality within noise for language modelling and retrieval tasks.
  arXiv  Detail & Related papers  (2026-05-20T08:04:40Z)
• Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs [8.332279450103151]
  Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks.<n>On-device LLM inference is heavily constrained by the memory and bandwidth overhead of the key-value (KV) cache.<n>We propose adaptive KV-cache quantization, a learned policy that assigns bit-width proportional to token importance.
  arXiv  Detail & Related papers  (2026-04-06T14:45:49Z)
• CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks [9.784730417146335]
  CoDeQ is a simple, fully differentiable method for joint pruning--quantization.<n>We parameterize the dead-zone width and learn it via backpropagation, alongside the quantization parameters.<n>On ImageNet with ResNet-18, CoDeQ reduces bit operations to 5% while maintaining close to full precision accuracy.
  arXiv  Detail & Related papers  (2025-12-15T04:53:32Z)
• DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance [125.81664663201282]
  We introduce a new KV cache compression method dubbed DBudgetKV.<n>It features an attention-based metric to signal when the remaining KV cache is unlikely to match the full-cache performance.<n>Our method achieves lossless KV pruning effectively and robustly, exceeding 25% compression ratio on average.
  arXiv  Detail & Related papers  (2025-02-24T06:33:39Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks [10.229120811024162]
  deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization. We propose a novel methodology to apply them jointly via a lightweight gradient-based search.
  arXiv  Detail & Related papers  (2024-07-01T08:07:02Z)
• Data-Free Dynamic Compression of CNNs for Tractable Efficiency [46.498278084317704]
  structured pruning approaches have shown promise in lowering floating-point operations without substantial drops in accuracy.<n>We propose HASTE (Hashing for Tractable Efficiency), a data-free, plug-and-play convolution module that instantly reduces a network's test-time inference cost without training or fine-tuning.<n>We demonstrate our approach on the popular vision benchmarks CIFAR-10 and ImageNet, where we achieve a 46.72% reduction in FLOPs with only a 1.25% loss in accuracy.
  arXiv  Detail & Related papers  (2023-09-29T13:09:40Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Sub-8-bit quantization for on-device speech recognition: a regularization-free approach [19.84792318335999]
  General Quantizer (GQ) is a regularization-free, "soft-to-hard" compression mechanism with self-adjustable centroids. GQ can compress both RNN-T and Conformer into sub-8-bit, and for some RNN-T layers, to 1-bit for fast and accurate inference.
  arXiv  Detail & Related papers  (2022-10-17T15:42:26Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.