Mixture of Experts with Mixture of Precisions for Tuning Quality of Service
- URL: http://arxiv.org/abs/2407.14417v1
- Date: Fri, 19 Jul 2024 15:42:49 GMT
- Title: Mixture of Experts with Mixture of Precisions for Tuning Quality of Service
- Authors: HamidReza Imani, Abdolah Amirany, Tarek El-Ghazawi,
- Abstract summary: This paper presents an adaptive serving approach for the efficient deployment of MoE models.
By dynamically determining the number of quantized experts, we offer a fine-grained range of configurations for tuning throughput and model quality.
Results highlight the practical applicability of our approach in dynamic and accuracy-sensitive applications.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The increasing demand for deploying large Mixture-of-Experts (MoE) models in resource-constrained environments necessitates efficient approaches to address their high memory and computational requirements challenges. Moreover, given that tasks come in different user-defined constraints and the available resources change over time in multi-tenant environments, it is necessary to design an approach which provides a flexible configuration space. This paper presents an adaptive serving approach for the efficient deployment of MoE models, capitalizing on partial quantization of the experts. By dynamically determining the number of quantized experts and their distribution across CPU and GPU, our approach explores the Pareto frontier and offers a fine-grained range of configurations for tuning throughput and model quality. Our evaluation on an NVIDIA A100 GPU using a Mixtral 8x7B MoE model for three language modelling benchmarks demonstrates that the throughput of token generation can be adjusted from 0.63 to 13.00 token per second. This enhancement comes with a marginal perplexity increase of 2.62 to 2.80, 6.48 to 7.24, and 3.24 to 3.53 for WikiText2, PTB, and C4 datasets respectively under maximum quantization. These results highlight the practical applicability of our approach in dynamic and accuracy-sensitive applications where both memory usage and output quality are important.
Related papers
- Harder Tasks Need More Experts: Dynamic Routing in MoE Models [58.18526590138739]
We introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models.
Our method dynamically selects experts based on the confidence level in expert selection for each input.
arXiv Detail & Related papers (2024-03-12T13:41:15Z) - Efficient Post-training Quantization with FP8 Formats [14.543387418837154]
We study the advantages of FP8 data formats for post-training quantization across 75 unique network architectures.
E4M3 is better suited for NLP models, whereas E3M4 performs marginally better than E4M3 on computer vision tasks.
arXiv Detail & Related papers (2023-09-26T00:58:36Z) - SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference.
We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit.
Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
arXiv Detail & Related papers (2023-06-13T08:57:54Z) - Energy-efficient Task Adaptation for NLP Edge Inference Leveraging
Heterogeneous Memory Architectures [68.91874045918112]
adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks.
We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
arXiv Detail & Related papers (2023-03-25T14:40:59Z) - Modular Quantization-Aware Training: Increasing Accuracy by Decreasing
Precision in 6D Object Pose Estimation [56.80039657816035]
Edge applications demand efficient 6D object pose estimation on resource-constrained embedded platforms.
We introduce Modular Quantization-Aware Training (MQAT), an adaptive and mixed-precision quantization-aware training strategy.
MQAT guides a systematic gradated modular quantization sequence and determines module-specific bit precisions, leading to quantized models that outperform those produced by state-of-the-art uniform and mixed-precision quantization techniques.
arXiv Detail & Related papers (2023-03-12T21:01:54Z) - Efficiently Scaling Transformer Inference [8.196193683641582]
We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings.
We develop a simple analytical model for inference efficiency to select the best multi-dimensional partitioning techniques optimized for TPU v4 slices.
We achieve a low-batch-size latency of 29ms per token during generation (using int8 weight quantization) and a 76% MFU during large-batch-size processing of input tokens.
arXiv Detail & Related papers (2022-11-09T18:50:38Z) - ZeroQuant: Efficient and Affordable Post-Training Quantization for
Large-Scale Transformers [29.566132632781848]
We present an efficient and affordable post-training quantization approach to compress large Transformer-based models, termed as ZeroQuant.
ZeroQuant is an end-to-end quantization and inference pipeline with three main components.
arXiv Detail & Related papers (2022-06-04T00:28:21Z) - Deep Variational Models for Collaborative Filtering-based Recommender
Systems [63.995130144110156]
Deep learning provides accurate collaborative filtering models to improve recommender system results.
Our proposed models apply the variational concept to injectity in the latent space of the deep architecture.
Results show the superiority of the proposed approach in scenarios where the variational enrichment exceeds the injected noise effect.
arXiv Detail & Related papers (2021-07-27T08:59:39Z) - Generative Design of Hardware-aware DNNs [6.144349819246314]
We propose a new way for autonomous quantization and HW-aware tuning.
A generative model, AQGAN, takes a target accuracy as the condition and generates a suite of quantization configurations.
We evaluate our model on five of the widely-used efficient models on the ImageNet dataset.
arXiv Detail & Related papers (2020-06-06T20:39:25Z) - Training with Quantization Noise for Extreme Model Compression [57.51832088938618]
We tackle the problem of producing compact models, maximizing their accuracy for a given model size.
A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator.
In this paper, we extend this approach to work beyond int8 fixed-point quantization with extreme compression methods.
arXiv Detail & Related papers (2020-04-15T20:10:53Z)
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.