BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Paper • 2609.04971 • Published • 32
Sihwa Lee
macto
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 months ago
ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling upvoted a paper 3 months ago
Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM ServingOrganizations
None yet