You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to use H2O on my databricks cluster mainly to use the 64GB Cuda GPU that I have. I dont want to convert my datasets to spark datasets though as everything else is in pandas. Is it possible to run h2o on databricks and use GPU without pysparkling? If so, what ip address do I use in my h2o.init(ip = ) . I did try this and the h2o datasets appear to be filled with all nulls.
The text was updated successfully, but these errors were encountered:
hello @matt7salomon, we didn't really try this
would there be any benefit of using h2o on databricks without spark?
are you able to use the compute without databricks? that's usually possible in cloud environments, probably also more cost effective
Yes. I found out how to install it on the cluster and it works. I need to just open a terminal and download the h2o.jar and move it to the directory itself looking in
I am trying to use H2O on my databricks cluster mainly to use the 64GB Cuda GPU that I have. I dont want to convert my datasets to spark datasets though as everything else is in pandas. Is it possible to run h2o on databricks and use GPU without pysparkling? If so, what ip address do I use in my h2o.init(ip = ) . I did try this and the h2o datasets appear to be filled with all nulls.
The text was updated successfully, but these errors were encountered: