MoE structure, not parameter count, governs INT4 robustness in sub-3B VLMs; SigLIP INT8 latency spikes on Jetson Ampere are a BitsAndBytes-Ampere interaction, and INT4 VRAM savings come with TPOT and energy penalties.
and Alistarh, D
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Mixture-of-Experts (MoE) architectures offer a general solution to the high inference costs of large language models (LLMs) via sparse routing, bringing faster and more accurate models, at the cost of massive parameter counts. For example, the SwitchTransformer-c2048 model has 1.6 trillion parameters, requiring 3.2TB of accelerator memory to run efficiently, which makes practical deployment challenging and expensive. In this paper, we present a solution to this memory problem, in form of a new compression and execution framework called QMoE. Specifically, QMoE consists of a scalable algorithm which accurately compresses trillion-parameter MoEs to less than 1 bit per parameter, in a custom format co-designed with bespoke GPU decoding kernels to facilitate efficient end-to-end compressed inference, with minor runtime overheads relative to uncompressed execution. Concretely, QMoE can compress the 1.6 trillion parameter SwitchTransformer-c2048 model to less than 160GB (20x compression, 0.8 bits per parameter) at only minor accuracy loss, in less than a day on a single GPU. This enables, for the first time, the execution of a trillion-parameter model on affordable commodity hardware, like a single server with 4x NVIDIA A6000 or 8x NVIDIA 3090 GPUs, at less than 5% runtime overhead relative to ideal uncompressed inference. The source code and compressed models are available at github.com/IST-DASLab/qmoe.
representative citing papers
AlphaQ performs calibration-free mixed-precision quantization of MoE models by allocating higher bits to experts whose weight spectra exhibit stronger heavy-tailed structure according to HT-SR theory, outperforming calibration-based methods and reaching near full-precision accuracy at 3.5 average bi
GEMQ applies global LP-based expert importance estimation and router fine-tuning within progressive quantization to cut memory and speed inference in MoE LLMs with little accuracy loss.
GSQ uses Gumbel-Softmax to optimize scalar quantization grids for LLMs, closing most of the accuracy gap to vector methods like QTIP at 2-3 bits per parameter while using symmetric scalar grids compatible with existing kernels.
PreScope combines a layer-aware activation predictor, cross-layer prefetch scheduling, and asynchronous I/O to deliver 141% higher throughput and 74.6% lower latency for MoE inference on legacy hardware.
citing papers explorer
-
Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment
MoE structure, not parameter count, governs INT4 robustness in sub-3B VLMs; SigLIP INT8 latency spikes on Jetson Ampere are a BitsAndBytes-Ampere interaction, and INT4 VRAM savings come with TPOT and energy penalties.
-
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
AlphaQ performs calibration-free mixed-precision quantization of MoE models by allocating higher bits to experts whose weight spectra exhibit stronger heavy-tailed structure according to HT-SR theory, outperforming calibration-based methods and reaching near full-precision accuracy at 3.5 average bi
-
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
GEMQ applies global LP-based expert importance estimation and router fine-tuning within progressive quantization to cut memory and speed inference in MoE LLMs with little accuracy loss.
-
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
GSQ uses Gumbel-Softmax to optimize scalar quantization grids for LLMs, closing most of the accuracy gap to vector methods like QTIP at 2-3 bits per parameter while using symmetric scalar grids compatible with existing kernels.
-
LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers
PreScope combines a layer-aware activation predictor, cross-layer prefetch scheduling, and asynchronous I/O to deliver 141% higher throughput and 74.6% lower latency for MoE inference on legacy hardware.