Pith. sign in

REVIEW 5 cited by

Scalable MatMul-free Language Modeling

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

arxiv 2406.02528 v7 pith:IF3DBONC submitted 2024-06-04 cs.CL

Scalable MatMul-free Language Modeling

classification cs.CL
keywords modelsmemoryapproachduringlanguagellmsmatmulmatmul-free
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs) have fundamentally altered how we approach scaling in machine learning. However, these models pose substantial computational and memory challenges, primarily due to the reliance on matrix multiplication (MatMul) within their attention and feed-forward (FFN) layers. We demonstrate that MatMul operations can be eliminated from LLMs while maintaining strong performance, even at billion-parameter scales. Our MatMul-free models, tested on models up to 2.7B parameters, are comparable to state-of-the-art pre-trained Transformers, and the performance gap narrows as model size increases. Our approach yields significant memory savings: a GPU-efficient implementation reduces memory consumption by up to 61% during training and over 10x during inference. When adapted for a multi-chip neuromorphic system, the model leverages asynchronous processing to achieve 4x higher throughput with 10x less energy than edge GPUs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. On the Importance of Multistability for Horizon Generalization in Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    Multistability is necessary for temporal horizon generalization in POMDPs, sufficient in simple tasks along with transient dynamics in complex ones, while monostable parallelizable RNNs like SSMs and gated linear RNNs...

  2. Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

    cs.LG 2026-05 unverdicted novelty 7.0

    Cumulative state updates in CMRU restore gradient flow through time in quantized bistable RNNs, yielding more stable convergence and competitive or superior performance versus LRUs and minGRUs on long-range sequence tasks.

  3. Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

    cs.LG 2026-05 unverdicted novelty 5.0

    CMRU restores gradient flow in BMRU via cumulative state updates with skip-connections through time, yielding better convergence and benchmark performance while retaining quantized persistent memory.

  4. BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design

    cs.LG 2026-04 unverdicted novelty 5.0

    BWTA achieves near full-precision accuracy on BERT and LLMs using binary weights and ternary activations, with 16-24x kernel speedups via specialized CUDA kernels.

  5. Hands-on PDC in Undergraduate Computing Education

    cs.CY 2026-04 unverdicted novelty 4.0

    A three-year evaluation of an undergraduate assignment shows that using a real supercomputer for matrix multiplication benchmarks improves student understanding of parallelism and multithreading.