Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

• URL: http://arxiv.org/abs/2409.20361v2
• Date: Mon, 11 Nov 2024 12:45:51 GMT
• Title: Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference
• Authors: Ke Yi, Zengke Liu, Jianwei Zhang, Chengyuan Li, Tong Zhang, Junyang Lin, Jingren Zhou,
• Abstract summary: Large language models incur substantial computation and memory movement costs due to their large scale. Existing approaches separate outliers and normal values into two matrices or migrate outliers from activations to weights, suffering from high latency or accuracy degradation. We propose Rotated Smooth (RRS), a plug-and-play activation smoother for quantization, consisting of Smooth and Rotation operation. The proposed method outperforms the state-of-the-art method in the LLaMA and Qwen families and improves WikiText-2 perplexity from 57.33 to 6.66 for INT4 inference.
• Score: 54.2589824716527
• License:
• Abstract: Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial computation and memory movement costs due to their large scale. Quantization methods have been employed to reduce service costs and latency. Nevertheless, outliers in activations hinder the development of INT4 weight-activation quantization. Existing approaches separate outliers and normal values into two matrices or migrate outliers from activations to weights, suffering from high latency or accuracy degradation. Based on observing activations from large language models, outliers can be classified into channel-wise and spike outliers. In this work, we propose Rotated Runtime Smooth (RRS), a plug-and-play activation smoother for quantization, consisting of Runtime Smooth and the Rotation operation. Runtime Smooth (RS) is introduced to eliminate channel-wise outliers by smoothing activations with channel-wise maximums during runtime. The rotation operation can narrow the gap between spike outliers and normal values, alleviating the effect of victims caused by channel-wise smoothing. The proposed method outperforms the state-of-the-art method in the LLaMA and Qwen families and improves WikiText-2 perplexity from 57.33 to 6.66 for INT4 inference.

Related papers

• OutlierTune: Efficient Channel-Wise Quantization for Large Language Models [24.645237670811476]
  OutlierTune is an efficient per-channel post-training quantization method for the activations of large language models. The proposed framework is easy to implement and hardware-efficient, introducing almost no additional computational overheads during the inference.
  arXiv  Detail & Related papers  (2024-06-27T02:02:26Z)
• TernaryLLM: Ternarized Large Language Model [29.29122031050894]
  Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks. We introduce Dual Learnable Ternarization (DLT), which enables both scales and shifts to be learnable. We also propose Outlier-Friendly Feature Knowledge Distillation (OFF) to recover the information lost in extremely low-bit quantization.
  arXiv  Detail & Related papers  (2024-06-11T11:40:12Z)
• DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs [40.48697728884967]
  Quantization of large language models (LLMs) faces significant challenges, particularly due to the presence of outlier activations. Traditional approaches predominantly address Normal Outliers, which are activations across all tokens with relatively large magnitudes. We introduce DuQuant, a novel approach that utilizes rotation and permutation transformations to more effectively mitigate both massive and normal outliers.
  arXiv  Detail & Related papers  (2024-06-03T18:27:44Z)
• SpinQuant: LLM quantization with learned rotations [49.07335692298487]
  Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs) We identify a collection of applicable rotation parameterizations that lead to identical outputs in full-precision Transformer architectures while enhancing quantization accuracy. We propose SpinQuant, a novel approach that incorporates learned rotation matrices for optimal quantized network accuracy.
  arXiv  Detail & Related papers  (2024-05-26T02:15:49Z)
• FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping [49.66872823080736]
  Autoregressive Large Language Models (e.g., LLaMa, GPTs) are omnipresent achieving remarkable success in language understanding and generation. To mitigate overload incurred during generation, several early-exit and layer-dropping strategies have been proposed. We propose FFN-SkipLLM, which is an input-adaptive feed-forward skipping strategy.
  arXiv  Detail & Related papers  (2024-04-05T02:35:43Z)
• QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models [44.515165695546614]
  Quantization-Aware Training (QAT) offers a solution, but its extensive training costs make Post-Training Quantization (PTQ) a more practical approach for Large Language Models (LLMs) We propose QLLM, an accurate and efficient low-bitwidth PTQ method designed for LLMs.
  arXiv  Detail & Related papers  (2023-10-12T05:25:49Z)
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model [89.8764435351222]
  We propose a new family of unbiased estimators called WTA-CRS, for matrix production with reduced variance. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones.
  arXiv  Detail & Related papers  (2023-05-24T15:52:08Z)
• Scaling the Convex Barrier with Sparse Dual Algorithms [141.4085318878354]
  We present two novel dual algorithms for tight and efficient neural network bounding. Both methods recover the strengths of the new relaxation: tightness and a linear separation oracle. We can obtain better bounds than off-the-shelf solvers in only a fraction of their running time.
  arXiv  Detail & Related papers  (2021-01-14T19:45:17Z)
• AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights [53.8489656709356]
  Normalization techniques are a boon for modern deep learning. It is often overlooked, however, that the additional introduction of momentum results in a rapid reduction in effective step sizes for scale-invariant weights. In this paper, we verify that the widely-adopted combination of the two ingredients lead to the premature decay of effective step sizes and sub-optimal model performances.
  arXiv  Detail & Related papers  (2020-06-15T08:35:15Z)

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.