Back to AIBriefs
AnalysisDevelopers

OSCAR RotationZoo improves 2-bit KV cache quantization

Proposes offline spectral covariance-aware rotation for 2-bit KV cache quantization. GGUF downloads for Gemma-4-12B-it and other models available.

·
4 days ago
OSCAR RotationZoo improves 2-bit KV cache quantization — AIBriefs