LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
paper
Fields
id
sources/quant-llmint8-paperPublisher
arXiv
Kind
paper
Published
2022-08-15
Accessed
2026-10-03
notes
v2. Vector-wise quantization + mixed-precision 16-bit outlier decomposition.
Notes
v2. Vector-wise quantization + mixed-precision 16-bit outlier decomposition.
Cross-references
This record references no other records.