Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
Paper • 2609.32259 • Published • 103 •
3
🤝 Open to Collab
Vincent-Daniel Yun
yunblack
AI & ML interests
Efficient ML, Efficient AI
Recent Activity
upvoted a paper about 15 hours ago
Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming authored a paper about 23 hours ago
Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming submitted a paper 1 day ago
Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP TrimmingOrganizations
commented a
paper 3 days ago