GPTQ quantizes 175B-parameter GPT models to 3-4 bits per weight in one shot using approximate second-order information, achieving negligible accuracy degradation and 3-4x inference speedups.
Optimal Brain Compression: A framework for ac- curate post-training quantization and pruning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
GPTQ quantizes 175B-parameter GPT models to 3-4 bits per weight in one shot using approximate second-order information, achieving negligible accuracy degradation and 3-4x inference speedups.