Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?
Paper
•
2310.05079
•
Published
Cheng Zhang
Cheng98
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 1 month ago
Cheng98/HSPI-SGL
published
a dataset
about 1 month ago
Cheng98/HSPI-SGL
updated
a model
3 months ago
AICrossSim/clm-600m
Organizations
authored
a
paper
almost 2 years ago