BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference

• URL: http://arxiv.org/abs/2501.01144v3
• Date: Tue, 21 Jan 2025 07:34:54 GMT
• Title: BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
• Authors: Wonsuk Jang, Thierry Tambe,
• Abstract summary: Large language models (LLMs) present significant challenges in memory usage and computational costs. We propose BlockDialect, a block-wise fine-grained mixed format technique that assigns a per-block optimal number format from a formatbook for better data representation. We also introduce DialectFP4, a formatbook of FP4 variants (akin to dialects) that adapt to diverse data distributions.
• Score: 0.5217870815854703
• License:
• Abstract: The rapidly increasing size of large language models (LLMs) presents significant challenges in memory usage and computational costs. Quantizing both weights and activations can address these issues, with hardware-supported fine-grained scaling emerging as a promising solution to mitigate outliers. However, existing methods struggle to capture nuanced block data distributions. We propose BlockDialect, a block-wise fine-grained mixed format technique that assigns a per-block optimal number format from a formatbook for better data representation. Additionally, we introduce DialectFP4, a formatbook of FP4 variants (akin to dialects) that adapt to diverse data distributions. To leverage this efficiently, we propose a two-stage approach for online DialectFP4 activation quantization. Importantly, DialectFP4 ensures energy efficiency by selecting representable values as scaled integers compatible with low-precision integer arithmetic. BlockDialect achieves 10.78% (7.48%) accuracy gain on the LLaMA3-8B (LLaMA2-7B) model compared to MXFP4 format with lower bit usage per data, while being only 5.45% (2.69%) below full precision even when quantizing full-path matrix multiplication. Focusing on how to represent over how to scale, our work presents a promising path for energy-efficient LLM inference.

Related papers

• Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss [59.835032408496545]
  We propose a tile-based strategy that partitions the contrastive loss calculation into arbitrary small blocks. We also introduce a multi-level tiling strategy to leverage the hierarchical structure of distributed systems. Compared to SOTA memory-efficient solutions, it achieves a two-order-of-magnitude reduction in memory while maintaining comparable speed.
  arXiv  Detail & Related papers  (2024-10-22T17:59:30Z)
• I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models [20.070306492164427]
  Post-training quantization serves as a potent technique to accelerate the inference of large language models. Existing works still necessitate a considerable number of floating-point (FP) operations during inference. This limitation hinders the deployment of large language models on the edge and cloud devices. We propose I-LLM, a novel integer-only fully-quantized PTQ framework tailored for large language models.
  arXiv  Detail & Related papers  (2024-05-28T05:56:11Z)
• Accurate Block Quantization in LLMs with Outliers [0.6138671548064355]
  The demand for inference on extremely large scale LLMs has seen enormous growth in recent months. The problem is aggravated by the exploding raise in the lengths of the sequences being processed. Various quantization techniques have been proposed that allow accurate quantization for both weights and activations.
  arXiv  Detail & Related papers  (2024-03-29T12:15:06Z)
• DB-LLM: Accurate Dual-Binarization for Efficient LLMs [83.70686728471547]
  Large language models (LLMs) have significantly advanced the field of natural language processing. Existing ultra-low-bit quantization always causes severe accuracy drops. We propose a novel Dual-Binarization method for LLMs, namely DB-LLM.
  arXiv  Detail & Related papers  (2024-02-19T09:04:30Z)
• FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference [57.119047493787185]
  This paper shows how to reduce model size by 43.1% and bring $1.25sim1.56times$ wall clock time speedup on different hardware with negligible accuracy drop. In practice, our method can reduce model size by 43.1% and bring $1.25sim1.56times$ wall clock time speedup on different hardware with negligible accuracy drop.
  arXiv  Detail & Related papers  (2024-01-08T17:29:16Z)
• LLM-FP4: 4-Bit Floating-Point Quantized Transformers [38.23587031169402]
  We propose LLM-FP4 for quantizing both weights and activations in large language models (LLMs) down to 4-bit floating-point values. Compared to integer quantization, floating-point (FP) quantization is more flexible and can better handle long-tail or bell-shaped distributions. Our method, for the first time, can quantize both weights and activations in the LLaMA-13B to only 4-bit and achieves an average score of 63.1.
  arXiv  Detail & Related papers  (2023-10-25T17:59:32Z)
• QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models [57.04178959678024]
  We show that the majority of inference computations for large generative models can be performed with both weights and activations being cast to 4 bits. We achieve this via a hybrid quantization strategy called QUIK, which compresses most of the weights and activations to 4-bit. We provide GPU kernels matching the QUIK format with highly-efficient layer-wise runtimes, which lead to practical end-to-end throughput improvements of up to 3.4x.
  arXiv  Detail & Related papers  (2023-10-13T17:15:05Z)
• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression [76.73007709690306]
  We introduce the Sparse-Quantized Representation (SpQR), a new compressed format and quantization technique. SpQR achieves relative accuracy losses of less than 1% in perplexity for highly-accurate LLaMA and Falcon LLMs. This makes it possible to run 33B parameter LLM on a single 24 GB consumer GPU without any performance degradation at 15% speedup.
  arXiv  Detail & Related papers  (2023-06-05T17:53:28Z)
• The case for 4-bit precision: k-bit Inference Scaling Laws [75.4335600212427]
  Quantization methods reduce the number of bits required to represent each parameter in a model. The final model size depends on both the number of parameters of the original model and the rate of compression. We run more than 35,000 zero-shot experiments with 16-bit inputs and k-bit parameters to examine which quantization methods improve scaling for 3 to 8-bit precision.
  arXiv  Detail & Related papers  (2022-12-19T18:48:33Z)
• Block Format Error Bounds and Optimal Block Size Selection [7.056118133284956]
  One of the most promising and rapidly advancing frontiers here is the creation of new data formats. We focus on the family of block floating point numerical formats due to their combination of wide dynamic range, numerical accuracy, and efficient hardware implementation of inner products using simple integer arithmetic.
  arXiv  Detail & Related papers  (2022-10-11T14:15:09Z)

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.