Benjamin Satzger ce19289fec Add gpu_count to inference endpoints ...

Explicitly specify the number of gpus an inference endpoint requires
to run a model.

2024-10-31 12:44:39 +01:00

..

inference_endpoint_nexus_spec.rb

Add gpu_count to inference endpoints

2024-10-31 12:44:39 +01:00

inference_endpoint_replica_nexus_spec.rb

Remove all skip_if_frozen{_models} calls in the specs

2024-10-30 12:08:24 -07:00