KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Paper • 2606.03458 • Published • 42
Ahmet Yuzuguler
acyuzuguler
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks upvoted a paper 8 months ago
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free
Low-Precision LLM WeightsOrganizations
None yet
upvoted a paper about 21 hours ago