Skip to content
conftrace_

transformer quantization

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

post-training quantization (2) model compression (2) per-embedding-group quantization (1) token-wise clipping (1) low bit-width (1) outlier suppression (1) low-bit representation (1) mixed precision (1) quantization-aware training (1) on-device inference (1)

Papers

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models NeurIPS 2022 Understanding and Overcoming the Challenges of Efficient Transformer Quantization EMNLP 2021 Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation EMNLP 2020