Rohan's Bytes

Rohan's Bytes

Share this post

Rohan's Bytes
Rohan's Bytes
"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations"
AI Paper Explained

"RotateKV: Accurate and Robust 2-Bit KV Cache…

Rohan Paul
Feb 10

Share this post

Rohan's Bytes
Rohan's Bytes
"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations"

Below podcast on this paper is generated with Google's Illuminate.

Read →
Comments
User's avatar
© 2025 Rohan Paul
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share