← back to paper

Review history

arxiv: 2509.08867 · 2 revisions

Benchmarking Energy Efficiency of Large Language Models Using vLLM

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
   67428 ms 7145 in 10152 out 2026-08-15T16:00:57.555711+00:00
2. 2026-08-04 CONDITIONAL HIGH v1.3.0-alltime-deepseek novelty 5.0
   66886 ms 7119 in 5840 out 2026-08-04T20:32:45.781894+00:00