AT
AT
I had the same issue. It seems that cuda has some problems: if (first_success != cudaSuccess) { return errors::Internal( "WhereOp: Could not launch cub::DeviceReduce::Sum to calculate " "temp_storage_bytes, status: ",...
did you change the cudnn version?
anything on this?? I would also be interested :))
you need to checkout a previous commit, commit 36000a2ed08ec2d1f6ae23f9d7ffd164e72d4aba But it would be nice to have acces to the pytorch model if it works.
the Folder in that commit will change to PythonClient as it is using the old version of Carla 0.8.x the new one should be based on the 0.9.X (I am...
thanks for the answer, are you planning to move to version 0.9.x ?
@hofbi anything? It is really hard to find any information about collecting data in 0.9.x
I am also interested in this topic.
Update: As far as I understood, the current implementation, using the optimum engine does not support the late interaction mechanism. looking at the implementation in fastembed, the postprocessing of the...
@michaelfeil any feedback?