SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

• URL: http://arxiv.org/abs/2211.10438v7
• Date: Fri, 29 Mar 2024 19:21:58 GMT
• Title: SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
• Authors: Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han,
• Abstract summary: 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.
• Score: 14.929695160346276
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same time. We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs. Based on the fact that weights are easy to quantize while activations are not, SmoothQuant smooths the activation outliers by offline migrating the quantization difficulty from activations to weights with a mathematically equivalent transformation. SmoothQuant enables an INT8 quantization of both weights and activations for all the matrix multiplications in LLMs, including OPT, BLOOM, GLM, MT-NLG, Llama-1/2, Falcon, Mistral, and Mixtral models. We demonstrate up to 1.56x speedup and 2x memory reduction for LLMs with negligible loss in accuracy. SmoothQuant enables serving 530B LLM within a single node. Our work offers a turn-key solution that reduces hardware costs and democratizes LLMs. Code is available at https://github.com/mit-han-lab/smoothquant.

Related papers

• FlatQuant: Flatness Matters for LLM Quantization [58.28221892035609]
  We propose FlatQuant, a new post-training quantization approach to enhance flatness of weights and activations. Our approach identifies optimal affine transformations tailored to each linear layer, calibrated in hours via a lightweight objective runtime. For inference latency, FlatQuant reduces the slowdown induced by pre-quantization transformation from 0.26x of QuaRot to merely $textbf0.07x$, bringing up to $textbf2.3x$ speedup for prefill and $textbf1.7x$ speedup for decoding.
  arXiv  Detail & Related papers  (2024-10-12T08:10:28Z)
• 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)
• FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization [6.931020818874328]
  We introduce a method called FlattenQuant, which significantly reduces the maximum value of the tensor by flattening the large channels in the tensor, to achieve low bit per-tensor quantization with minimal accuracy loss. Our work achieves up to 2$times$ speedup and 2.3$times$ memory reduction for LLMs with negligible loss in accuracy.
  arXiv  Detail & Related papers  (2024-02-28T02:00:34Z)
• OneBit: Towards Extremely Low-bit Large Language Models [66.29839811207617]
  This paper boldly quantizes the weight matrices of LLMs to 1-bit, paving the way for the extremely low bit-width deployment of LLMs. Experiments indicate that OneBit achieves good performance (at least 81% of the non-quantized performance on LLaMA models) with robust training processes.
  arXiv  Detail & Related papers  (2024-02-17T14:26:57Z)
• 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)
• Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference? [21.243853199880807]
  We study the statistical and learning properties of Large language models (LLMs) We adapt block quantisations for LLMs, a family of methods that share scaling factors across packed numbers. Our nearly-lossless quantised 6-bit LLMs achieve a $19times$ higher arithmetic density and $5times$ memory density than the float32 baseline.
  arXiv  Detail & Related papers  (2023-10-08T09:05:14Z)
• OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models [57.27101446992148]
  Large language models (LLMs) have revolutionized natural language processing tasks. Recent post-training quantization (PTQ) methods are effective in reducing memory footprint and improving the computational efficiency of LLM. We introduce an Omnidirectionally calibrated Quantization technique for LLMs, which achieves good performance in diverse quantization settings.
  arXiv  Detail & Related papers  (2023-08-25T02:28:35Z)
• AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration [54.692405042065815]
  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.
  arXiv  Detail & Related papers  (2023-06-01T17:59:10Z)

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.