Output-Aware Rotation for INT2 KV-Cache Quantization
Paper • 2608.02691 • Published • 2
Woosang Lim
wsl448
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 16 days ago
Output-Aware Rotation for INT2 KV-Cache QuantizationOrganizations
upvoted a paper 16 days ago
upvoted an article about 2 years ago
Article
A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes
ybelkada, timdettmers
• • 140