MCAP uses load-time Monte Carlo profiling to estimate layer importance, enabling dynamic quantization (W4A8 vs W4A16) and memory tiering (GPU/RAM/SSD) that delivers 1.5-1.8x higher decode throughput than llama-cpp Q4_0 on NVIDIA T4 while fitting models into previously infeasible memory budgets.
Neo: Saving gpu memory crisis with cpu offloading for online llm inference.arXiv preprint arXiv:2411.01142, 2024b
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
FlexiCache reduces GPU memory for long-context LLM requests by up to 70% and boosts throughput 1.38-1.55x and latency 1.6-2.1x by exploiting per-head differences in temporal stability of critical tokens.
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.
citing papers explorer
-
MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference
MCAP uses load-time Monte Carlo profiling to estimate layer importance, enabling dynamic quantization (W4A8 vs W4A16) and memory tiering (GPU/RAM/SSD) that delivers 1.5-1.8x higher decode throughput than llama-cpp Q4_0 on NVIDIA T4 while fitting models into previously infeasible memory budgets.
-
FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management
FlexiCache reduces GPU memory for long-context LLM requests by up to 70% and boosts throughput 1.38-1.55x and latency 1.6-2.1x by exploiting per-head differences in temporal stability of critical tokens.
-
Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.