REVIEW 11 cited by
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
read the original abstract
Post-training quantization (PTQ) serves as a potent technique to accelerate the inference of large language models (LLMs). Nonetheless, existing works still necessitate a considerable number of floating-point (FP) operations during inference, including additional quantization and de-quantization, as well as non-linear operators such as RMSNorm and Softmax. This limitation hinders the deployment of LLMs on the edge and cloud devices. In this paper, we identify the primary obstacle to integer-only quantization for LLMs lies in the large fluctuation of activations across channels and tokens in both linear and non-linear operations. To address this issue, we propose I-LLM, a novel integer-only fully-quantized PTQ framework tailored for LLMs. Specifically, (1) we develop Fully-Smooth Block-Reconstruction (FSBR) to aggressively smooth inter-channel variations of all activations and weights. (2) to alleviate degradation caused by inter-token variations, we introduce a novel approach called Dynamic Integer-only MatMul (DI-MatMul). This method enables dynamic quantization in full-integer matrix multiplication by dynamically quantizing the input and outputs with integer-only operations. (3) we design DI-ClippedSoftmax, DI-Exp, and DI-Normalization, which utilize bit shift to execute non-linear operators efficiently while maintaining accuracy. The experiment shows that our I-LLM achieves comparable accuracy to the FP baseline and outperforms non-integer quantization methods. For example, I-LLM can operate at W4A4 with negligible loss of accuracy. To our knowledge, we are the first to bridge the gap between integer-only quantization and LLMs. We've published our code on anonymous.4open.science, aiming to contribute to the advancement of this field.
Forward citations
Cited by 11 Pith papers
-
When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation
For a fixed low-bit residual library, the distance to the closed relaxed reachable set is an exact structural floor that pure depth approaches at O(1/D), while write-back arithmetic can reverse the gain and accuracy m...
-
QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention
QFlash implements end-to-end integer FlashAttention with integer-only softmax, delivering up to 8.69x speedup and 18.8% energy savings on ViT models while preserving accuracy under per-tensor quantization.
-
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
SplitQ improves low-bit PTQ for VLMs by isolating modality-specific outlier channels via MOCD and applying dual-branch adaptive calibration via ACC, outperforming prior methods on six datasets across W4A8 to W3A2 settings.
-
Theory-optimal Quantization Based on Flatness
The paper introduces the Flatness metric, derives a theory-optimal quantization solution, and presents BDQ that uses bidirectional diagonal transformations to reduce outlier impact, achieving under 1% drop at W4A4 on ...
-
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
LBLLM achieves better accuracy than prior binarization methods for LLMs by decoupling weight and activation quantization through initialization, layer-wise distillation, and learnable activation scaling.
-
LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM
LOCALUT delivers 1.82x geometric mean speedup for quantized DNN inference on real UPMEM DRAM-PIM devices by using operation-packed LUTs with canonicalization, reordering, and slice streaming.
-
IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference
A lookup-table-based integer softmax replaces the floating-point softmax in quantized transformer attention, delivering up to 3.7x speedup and 61% energy reduction on ARMv8 CPUs with roughly unchanged accuracy.
-
LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression
Loss-aware rank allocation plus residual-stream output correction yields substantially lower WikiText-2 perplexity than prior SVD LLM compressors at 60% compression.
-
EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
EVA is a vector-quantization hardware architecture that transforms LLM decoding from GEMV to GEMM via direct codebook dot products and conflict-free output buffering, claiming up to 11.17x speedup over prior lookup designs.
-
MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
MGVQ introduces sensitivity-aware structured mixed-precision VQ and gradient-aware second-order error compensation using Kronecker and Block-LDL decompositions, reporting up to 4.9 point gains over prior methods at 2-...
-
Break Through the Compression Bottleneck: From Theory to Practice
The paper asserts a first proof that low-rank decomposition and quantization are non-orthogonal tools for LLM compression, recommends low-rank-first ordering, and adds a diagonal scaling fix (DAM) that reduces the com...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.