{"total":15,"rows":[{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55,"area":null},{"id":"2511.05597","title":"From Prompts to Power: Measuring the Energy Footprint of LLM Inference","created":"2025-11-05","cited_by_count":12,"area":null},{"id":"2602.05695","title":"SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2601.22362","title":"Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2601.22357","title":"Small Talk, Big Impact: The Energy Cost of Thanking AI","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.17697","title":"Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2607.02391","title":"WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.09172","title":"Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2511.19438","title":"Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2603.00356","title":"Token Management in Multi-Tenant AI Inference Platforms","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.02949","title":"SEALing the Gap: A Reference Framework for LLM Inference Carbon Estimation via Multi-Benchmark Driven Embodiment","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2606.10861","title":"From Perception to Action: Can UI Interventions Foster Sustainable LLM Chatbot","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.12350","title":"From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.33965","title":"Greenpixie's AI Token Methodology: Assessing the Energy, Water and CO2-eq Impact of AI Tokens for Open and Closed Weight Models","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}