KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Paper • 2606.03458 • Published • 67
Georgios Zacharopoulos
giorgiozacharo
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks upvoted a paper 10 months ago
AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs upvoted a paper 10 months ago
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free
Low-Precision LLM WeightsOrganizations
None yet