Article
Why Post-RoPE Token Merging Hits 0% on NVIDIA RULER — And How Pre-RoPE Algebraic Multigrid Gives 28.6× to 50× KV Compression (SPICY-KV)
ElithiaTechnologies
• • 1Yuge Y PRO
ElithiaTechnologies
AI & ML interests
None yet
Recent Activity
updated a model about 12 hours ago
ElithiaTechnologies/SPICY-KV commentedon a paper 3 days ago
Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on
Long-Context TasksOrganizations
None yet
published an article 3 days ago