140 citations · 311 across the 22 of their papers we have counts for
17 papers · 1 filter
Compression Scaling Laws:Unifying Sparsity and Quantization
Elias Frantar, Utku Evci, Wonpyo Park +2
We investigate how different compression techniques -- such as weight and activation quantization, and weight sparsity -- affect the scaling behavior of large language models (LLMs…
MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models
Elias Frantar, Roberto L. Castro, Jiale Chen +2
As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GP…
Extreme Compression of Large Language Models via Additive Quantization
Vage Egiazarian, Andrei Panferov, Denis Kuznedelev +3
The emergence of accurate open large language models (LLMs) has led to a race towards performant quantization techniques which can enable their execution on end-user devices. In th…
QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models
Saleh Ashkboos, Ilia Markov, Elias Frantar +5
Large Language Models (LLMs) from the GPT family have become extremely popular, leading to a race towards reducing their inference costs to allow for efficient local computation. Y…
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
Elias Frantar, Dan Alistarh
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 mo…
Scaling Laws for Sparsely-Connected Foundation Models
Elias Frantar, Carlos Riquelme, Neil Houlsby +2
We explore the impact of parameter sparsity on the scaling behavior of Transformers trained on massive datasets (i.e., "foundation models"), in both vision and language domains. In…
Accurate Neural Network Pruning Requires Rethinking Sparse Optimization
Denis Kuznedelev, Eldar Kurtic, Eugenia Iofinova +3
Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performa…
QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models
Tommaso Pegolotti, Elias Frantar, Dan Alistarh +1
We present ongoing work on a new automatic code generation approach for supporting quantized generative inference on LLMs such as LLaMA or OPT on off-the-shelf CPUs. Our approach i…
JaxPruner: A concise library for sparsity research
Joo Hyung Lee, Wonpyo Park, Nicole Mitchell +22
This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims to accelerate research on sparse neural…
ZipLM: Inference-Aware Structured Pruning of Language Models
Eldar Kurtic, Elias Frantar, Dan Alistarh
The breakthrough performance of large language models (LLMs) comes with major computational footprints and high deployment costs. In this paper, we progress towards resolving this…
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
Elias Frantar, Dan Alistarh
We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at min…
L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning
Mohammadreza Alimohammadi, Ilia Markov, Elias Frantar +1
Data-parallel distributed training of deep neural networks (DNN) has gained very widespread adoption, but can still experience communication bottlenecks. To address this issue, ent…
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Elias Frantar, Saleh Ashkboos, Torsten Hoefler +1
Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their ext…
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
Elias Frantar, Sidak Pal Singh, Dan Alistarh
We consider the problem of model compression for deep neural networks (DNNs) in the challenging one-shot/post-training setting, in which we are given an accurate trained model, and…
SPDY: Accurate Pruning with Speedup Guarantees
Elias Frantar, Dan Alistarh
The recent focus on the efficiency of deep neural networks (DNNs) has led to significant work on model compression approaches, of which weight pruning is one of the most popular. A…
M-FAC: Efficient Matrix-Free Approximations of Second-Order Information
Elias Frantar, Eldar Kurtic, Dan Alistarh
Efficiently approximating local curvature information of the loss function is a key tool for optimization and compression of deep neural networks. Yet, most existing methods to app…
On the Sample Complexity of Adversarial Multi-Source PAC Learning
Nikola Konstantinov, Elias Frantar, Dan Alistarh +1
We study the problem of learning from multiple untrusted data sources, a scenario of increasing practical relevance given the recent emergence of crowdsourcing and collaborative le…