conftrace_

prefill optimization

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

kv cache (2) model transformation (1) attention mapping (1) large language model (1) key-value cache compression (1) inference acceleration (1) model scaling (1) inference optimization (1) knowledge distillation (1) model compression (1)

Papers

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs ACL 2025 SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation EMNLP 2025