Hi all,

We recently released Language Weaver Edge 8.6.

If you are upgrading from Edge 8.5 and you are training Adaptable LPs with a GPU, you will need to update the Nvidia Drivers in order to use the GPU for training.

Edge 8.6 now requiring Nvidia CUDA 11 and the minimum version of drivers required is 510.47.03. The GPU driver installation instructions have been updated in the documentation.

Note that using a GPU for training still requires a host running a Linux distribution.

And with 8.6, you can now use CPU to train Adaptable LPs. And this works with Linux and Windows. Training takes longer (24x times slower) but the output model is identical to a training performed on GPU. Only 4 CPUs are needed and 32 GB of RAM. All you need is to create a "Training engine" on a host with enough hardware available and start it.

Let us know if you have any question,

Thank you