2024
2023
- 18 Mar HAWQ-V3: Dyadic Neural Network Quantization
- 26 Feb TensorRT 기초
- 12 Feb LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale 정리
- 29 Jan 8-bit Optimizers via Block-wise Quantization 정리
- 22 Jan Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks 정리 (Chapter 1 ~ 3)
- 08 Jan A Comprehensive Survey on Graph Neural Networks 정리
- 01 Jan Recent Advances on Neural Network Pruning at Initialization 정리
2022