activity
20142024
most citedSpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

26 citations · 50 across the 20 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2024

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem

Vladimir Malinovskii, Andrei Panferov, Ivan Ilin +3

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into indiv…

cs.LG2024

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…

cs.LG20232 cited

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…

cs.LG20231 cited

AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms

Rustem Islamov, Mher Safaryan, Dan Alistarh

We analyze asynchronous-type algorithms for distributed SGD in the heterogeneous setting, where each worker has its own computation and communication speeds, as well as data distri…

cs.LG20236 cited

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…

cs.LG2023

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…