Skip to content

Looking for dockerfile.jetson with RedisAI 1.2.5 and ONNX backend #929

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cr-ooi opened this issue Jun 16, 2022 · 0 comments
Open

Looking for dockerfile.jetson with RedisAI 1.2.5 and ONNX backend #929

cr-ooi opened this issue Jun 16, 2022 · 0 comments

Comments

@cr-ooi
Copy link

cr-ooi commented Jun 16, 2022

Is your feature request related to a problem? Please describe.
Our team has worked on Intel x86 device with RedisEdge (Redis 6.2.6, RedisAI 1.2.5, RedisGears 1.2.4, and RedisTimeSeries 1.6.11) and they are really impressing with the performance, especially that Intel x86 device just equipped with an outdated 4th Gen i7 processor which without Intel® DL Boost.

observability

Current redisfab/redisedgevision:0.4.0-jetson-arm64v8-bionic only supports RedisAI 1.0.2 and when we ran it with Torch backend (It looks like ONNX backend could not be loaded) - it also thrown out error message "GPU requested but Torch couldn't find CUDA".

We would like to request
Describe the solution you'd like
We would like to seek for help regarding to have dockerfile.jetson with RedisAI 1.2.5 and ONNX backend, thus we can compare the performance difference between various device platform under the same codes. We noticed that there are few dockerfile.jetson available across RedisEdge GitHub and RedisAI GitHub (Branches) - they specified the Jetson model as Nano or Xavier. Would that be possible to open for various Jetson models?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant