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

Support dynamic element size when getting tensor data in runtime #1592

Closed

brataTT opened this issue Dec 12, 2024 · 1 comment

Assignees

Contributor

brataTT commented Dec 12, 2024

Currently, getTensorData in runtime assumes element size of tensor data is always 4 bytes(c++ float).

This should be updated to correctly calculate allocated memory of data returned.

Blocks tt-torch#95 where seg fault occurs trying to access 1MB of data out of 0.5MB allocated.

brataTT self-assigned this

Contributor Author

brataTT commented Dec 16, 2024

Making this change is not required since we can use memcpy instead to copy Tensors.

brataTT closed this as not planned

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment