MORI improves throughput 20-71% and TTFT 18-43% over baselines by ranking programs on a continuous idleness spectrum and shifting the GPU-CPU boundary to match capacity in agentic LLM serving.
2025.PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
TokenStack's heterogeneous HBM-PIM design with base-die control and topology-aware KV placement delivers 1.62x higher geometric-mean token throughput and 1.70x SLO-compliant serving capacity than AttAcc while cutting per-token energy by 30-47%.
citing papers explorer
-
Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI
MORI improves throughput 20-71% and TTFT 18-43% over baselines by ranking programs on a continuous idleness spectrum and shifting the GPU-CPU boundary to match capacity in agentic LLM serving.
-
TokenStack: A Heterogeneous HBM-PIM Architecture and Runtime for Efficient LLM Inference
TokenStack's heterogeneous HBM-PIM design with base-die control and topology-aware KV placement delivers 1.62x higher geometric-mean token throughput and 1.70x SLO-compliant serving capacity than AttAcc while cutting per-token energy by 30-47%.