Cite
Notes
Only stored in your browser.
Attribution
RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval
arXiv 2024
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
arXiv 2023
from 2 papers
Chuang Gan
Guangxuan Xiao
Haotian Tang
Ji Lin
Jiaming Tang
Kaifeng Lyu
Kaiyue Wen
Shang Yang
Song Han
Wei-Chen Wang