NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention

Oct-10-2025, 16:49:52 GMT–Neural Information Processing Systems

We leverage this unique capability to propose NoMAD-Attention, an efficient attention algorithm that replaces MAD operations with in-register lookups.

large language model, machine learning, natural language, (19 more...)

Neural Information Processing Systems

Oct-10-2025, 16:49:52 GMT

Conferences PDF

Country:
- North America > United States
  - New Jersey > Hudson County
    - Hoboken (0.04)
  - Texas > Harris County
    - Houston (0.04)
- South America > Chile
  - Santiago Metropolitan Region > Santiago Province > Santiago (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Information Technology (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (1.00)
    - Natural Language > Large Language Model (1.00)
    - Representation & Reasoning (0.93)
  - Data Science (1.00)
  - Hardware (0.93)

Duplicate Docs Excel Report

Title
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention

Similar Docs Excel Report more

Title	Similarity	Source
None found