conftrace_

memory bottleneck

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

constant sized cache (1) eviction-based methods (1) recurrence (1) llm inference (1) computational overhead (1) deep network (1) key-value cache (1) memory footprint (1) memory optimization (1)

Papers

Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference ICML 2024 Memory Optimization for Deep Networks ICLR 2021