Is NVIDIA on-device platform such as Jetson Orin in the roadmap? #5263
Description
🚀 The feature, motivation and pitch
Nowadays, many inference frameworks like vLLM, SGLang, and LMDeploy are available for Nvidia GPUs, but they primarily target cloud use cases. On the other hand, platforms like Jetson Orin are mostly used for edge devices, yet there are no frameworks specifically for on-device GPUs. So, I was wondering if ExecuTorch plans to support on-device GPU platforms like Jetson Orin?
Alternatives
No response
Additional context
No response
RFC (Optional)
No response