BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Paper • 2609.04971 • Published • 40
kdw4537
CYDA
AI & ML interests
None yet
Recent Activity
liked a model over 1 year ago
lmsys/longchat-7b-v1.5-32k upvoted a paper over 1 year ago
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on
a Single GPUOrganizations
None yet
upvoted a paper 8 days ago