Collection by
Oct 9
Oct 9
-
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 143 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 602 -
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 73 -
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory
Paper • 2405.08707 • Published • 27
