Trending repositories: efficiency

1 tracked repository tagged with efficiency, ordered by stars. Use the topic filters below to narrow further.

Filter by topic

1 of 1 repository

  • microsoft/BitNet

    Official inference framework for 1-bit LLMs

    AI summary: The official C++ inference framework designed specifically to run ultra-efficient 1.58-bit and 1-bit Large Language Models natively.

    40,229ai-mlC++MIT