List your company

LLM Inference on OPT-125M

46.71Latency (ms)Baseline
40.412482.9212125.43167.9388Mar 17, 2026

Evaluation results

MethodLinks
Baseline2026.0346.71——
RoR2026.0352.280.2311.9
RADAR2026.0376.25063.1
FaR2026.03204.152.1336.9