TensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor
TensorRT Edge-LLM achieves 6.4x faster MLPerf benchmark on Jetson AGX Thor.
NVIDIA's TensorRT Edge-LLM has demonstrated significant performance improvements, completing the MLPerf Edge Agentic Benchmark 6.4 times faster on the Jetson AGX Thor. This advancement highlights the shift of AI agents from cloud to edge devices, responding to the increasing demand for fast inference in diverse applications.