AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

• URL: http://arxiv.org/abs/2306.00978v5
• Date: Thu, 18 Jul 2024 17:51:33 GMT
• Title: AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
• Authors: Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han,
• Abstract summary: We propose Activation-aware Weight Quantization (AWQ), a hardware-friendly approach for LLM low-bit weight-only quantization. AWQ protects only 1% salient weights and achieves excellent quantization performance for instruction-tuned LMs and, for the first time, multi-modal LMs. We also implement TinyChat, an efficient and flexible inference framework tailored for 4-bit on-device LLM/VLMs.
• Score: 54.692405042065815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have transformed numerous AI applications. On-device LLM is becoming increasingly important: running LLMs locally on edge devices can reduce the cloud computing cost and protect users' privacy. However, the astronomical model size and the limited hardware resource pose significant deployment challenges. We propose Activation-aware Weight Quantization (AWQ), a hardware-friendly approach for LLM low-bit weight-only quantization. AWQ finds that not all weights in an LLM are equally important. Protecting only 1% salient weights can greatly reduce quantization error. To identify salient weight channels, we should refer to the activation distribution, not weights. To avoid the hardware-inefficient mix-precision quantization, we mathematically derive that scaling up the salient channels can reduce the quantization error. AWQ employs an equivalent transformation to scale the salient weight channels to protect them. The scale is determined by collecting the activation statistics offline. AWQ does not rely on any backpropagation or reconstruction, so it generalizes to different domains and modalities without overfitting the calibration set. AWQ outperforms existing work on various language modeling and domain-specific benchmarks (coding and math). Thanks to better generalization, it achieves excellent quantization performance for instruction-tuned LMs and, for the first time, multi-modal LMs. Alongside AWQ, we implement TinyChat, an efficient and flexible inference framework tailored for 4-bit on-device LLM/VLMs. With kernel fusion and platform-aware weight packing, TinyChat offers more than 3x speedup over the Huggingface FP16 implementation on both desktop and mobile GPUs. It also democratizes the deployment of the 70B Llama-2 model on mobile GPUs.

Related papers

• MobileQuant: Mobile-friendly Quantization for On-device Language Models [31.75012542498791]
  Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. deploying LLMs on edge devices poses several challenges with respect to memory, energy, and compute costs. We introduce a simple post-training quantization method, named MobileQuant, that extends previous weight equivalent transformation works.
  arXiv  Detail & Related papers  (2024-08-25T20:41:22Z)
• LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices [41.17378536966264]
  Low-Rank Quantization $-$ is a simple yet effective post-training weight quantization method for large language models. Thanks to parameter sharing via low-rank structure, LRQ only needs to learn significantly fewer parameters while enabling the individual scaling of weights. We show the superiority of LRQ over prior LLM PTQ works under (i) $8$-bit weight and per-tensor activation quantization, (ii) $4$-bit weight and $8$-bit per-token activation quantization, and (iii) low-bit weight-only quantization schemes.
  arXiv  Detail & Related papers  (2024-07-16T09:32:07Z)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment [56.44025052765861]
  Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs. We show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x.
  arXiv  Detail & Related papers  (2024-05-06T16:03:32Z)
• Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization [62.15918574997175]
  It is known that language models contain outlier channels whose values on average are orders of magnitude higher than other channels. We propose a strategy which regularizes a layer's inputs via quantization-aware training (QAT) and its outputs via activation kurtosis regularization. We show that regularizing both the inputs and outputs is crucial for preventing a model's "migrating" the difficulty in input quantization to the weights.
  arXiv  Detail & Related papers  (2024-04-04T17:25:30Z)
• BiLLM: Pushing the Limit of Post-Training Quantization for LLMs [53.31402059062365]
  BiLLM is a groundbreaking 1-bit post-training quantization scheme tailored for pretrained large language models. It achieves for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families.
  arXiv  Detail & Related papers  (2024-02-06T09:26:34Z)
• SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM [13.035063417593534]
  Large language models (LLMs) have shown remarkable capabilities in various tasks. Currently, 4-bit post-training quantization (PTQ) has achieved some success in LLMs. We propose SmoothQuant+, an accurate and efficient 4-bit weight-only PTQ.
  arXiv  Detail & Related papers  (2023-12-06T11:10:55Z)
• QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models [85.02796681773447]
  We propose a quantization-aware low-rank adaptation (QA-LoRA) algorithm. The motivation lies in the imbalanced degrees of freedom of quantization and adaptation. QA-LoRA is easily implemented with a few lines of code.
  arXiv  Detail & Related papers  (2023-09-26T07:22:23Z)
• SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models [14.929695160346276]
  Large language models (LLMs) show excellent performance but are compute- and memory-intensive. We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization solution. We demonstrate up to 1.56x speedup and 2x memory reduction for LLMs with negligible loss in accuracy.
  arXiv  Detail & Related papers  (2022-11-18T18:59:33Z)

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.