Skip to content
conftrace_

per-embedding-group quantization

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

transformer quantization (1) low bit-width (1) low-bit representation (1) quantization-aware training (1) memory footprint (1) post-training quantization (1) model quantization (1) model compression (1)

Papers

Understanding and Overcoming the Challenges of Efficient Transformer Quantization EMNLP 2021