Ping Luo (羅平)
Ping Luo (羅平)
Home
News&Talks
Publications
Members
Projects
Contact
Light
Dark
Automatic
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Wenqi Shao
,
Mengzhao Chen
,
Zhaoyang Zhang
,
Peng Xu
,
Lirui Zhao
,
Zhiqian Li
,
Kaipeng Zhang
,
Peng Gao
,
Yu Qiao
,
Ping Luo
March 2024
PDF
Type
Conference paper
Publication
International Conference on Learning Representation
(
ICLR
) 2024
Related
Foundation Model is Efficient Multimodal Multitask Model Selector
Dynamic Token Normalization improves Vision Transformers
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
Embodiedgpt: Vision-language pre-training via embodied chain of thought
Visionllm: Large language model is also an open-ended decoder for vision-centric tasks
Cite
×
