Papers with DSQ

2 papers
Dynamic Stashing Quantization for Efficient Transformer Training (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks.
Approach: They propose a dynamic quantization strategy that reduces the amount of memory operations and reduces arithmetic cost by 20.95 on two translation tasks and three classification tasks.
Outcome: The proposed model reduces the amount of arithmetic operations by 20.95 and the number of DRAM operations by 2.55 on two translation tasks and three classification tasks.
Q-Mamba: Towards more efficient Mamba models via post-training quantization (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies show that Mamba architectures have room for further optimization in linear projections and state caches.
Approach: They propose a decoupled scale quantization scheme to mitigate outliers in states and channels by applying separate quantization scales.
Outcome: The proposed method reduces memory consumption by 50% across various quantization settings, model sizes, and generation and zero-shot tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations