conftrace_

throughput increase

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

llms (1) retrofitting (1) sequential task (1) key-value cache compression (1) inference (1) compression ratio (1) latency reduction (1) performance optimization (1)

Papers

Principles and Methodologies for Serial Performance Optimization OSDI 2025 Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference ICML 2024