LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
arXiv preprint arXiv:2002.05645 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
ZeRO removes memory redundancies in parallel training to scale deep learning models to over a trillion parameters with high throughput on current hardware.
citing papers explorer
-
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
-
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
ZeRO removes memory redundancies in parallel training to scale deep learning models to over a trillion parameters with high throughput on current hardware.