Maximizing LLM tokens/sec on Jetson under limited memory
-
Updated
Jun 17, 2026 - Jupyter Notebook
#
trtexec
Here are 2 public repositories matching this topic...
Jetson Orin Nano internal edge AI evidence lab: environment baselines, PyTorch/ONNX Runtime/TensorRT comparison, FastAPI serving, Whisper audio, and InferEdge exports.
benchmark cuda pytorch whisper jetson tensorrt evidence onnx embedded-ai fastapi edge-ai onnxruntime runtime-comparison ai-inference jetson-orin-nano trtexec inferedge
-
Updated
May 18, 2026 - Python
Add this topic to your repo
To associate your repository with the trtexec topic, visit your repo's landing page and select "manage topics."