Skip to main content

Hi Axelera Team,

 

I'm exploring the Axelera Metis AI device for edge deployment and had a quick question:

 

Is it possible to run our own custom Python scripts or shell commands on the device Or is the device strictly limited to running AI model inference pipelines through your SDK, without the ability to execute external scripts or commands?

 

Looking forward to your guidance. Thanks in advance!

Hi there ​@Manikanta R45, great to have you here!

Metis devices aren’t locked down to SDK-only or anything, so you can develop and run custom Python scripts and issue shell commands 🙂

That being said, the Voyager SDK is optimised to deliver the best results (very quickly), but you’re not locked into it if you wanted to “go rogue” 😄

What’s the project you’re looking at building?


Hi Spanner,

 

Thank you for the clarification that’s great to hear!

 

We’re currently working on deploying a real-time video analytics solution at the edge for smart retail and manufacturing use cases. The ability to run our own Python scripts alongside the inference pipeline gives us the flexibility we need to handle preprocessing, custom logic, and downstream integration.

 

I’ll continue exploring the Voyager SDK for optimized inference, but it’s good to know we’re not restricted if we need to step outside the standard pipeline.

 

Appreciate your support I’ll reach out if I hit any roadblocks.

 

Best regards,

Manikanta R

AttentionKart


Great project - so much potential in this kind of application. We have a demo of a self-service checkout that’s very popular at the shows.

Keep us posted on your progress! This sounds exactly like the kind of thing Metis was made for!

 


Reply