Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Is it possible to run NanoVLM on data center GPU like A-series, T-series or desktop GPU like 40-series? #42

Open
frankzflyward opened this issue Aug 30, 2024 · 1 comment
Open

Is it possible to run NanoVLM on data center GPU like A-series, T-series or desktop GPU like 40-series? #42

frankzflyward opened this issue Aug 30, 2024 · 1 comment

Comments

@frankzflyward
Copy link

Has anyone tried this yet?
@frankzflyward frankzflyward changed the title Is it possible to run NanoLLM on datacenter or desktop GPU like A-series, T-series or 40-series? Is it possible to run NanoLLM on data center GPU like A-series, T-series or desktop GPU like 40-series? Aug 30, 2024
@frankzflyward frankzflyward changed the title Is it possible to run NanoLLM on data center GPU like A-series, T-series or desktop GPU like 40-series? Is it possible to run NanoVLM on data center GPU like A-series, T-series or desktop GPU like 40-series? Aug 30, 2024
@dusty-nv
Copy link
Owner

@frankzflyward I've not been able to try porting it, I've been meaning to split the plugins/agents into another repo to make that easier on both accounts. Then in theory you would just need to have PyTorch, Transformers, MLC, and optionally AWQ installed (which all of those are available on x86, most of the containerization/build process is getting them & others running on Jetson/aarch64)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@dusty-nv @frankzflyward