Configuring the number of workers for machine learning and RoBERTa

Recommended RAM per worker

For each worker, we recommend 3GB of GPU RAM.

Configuring the number of machine learning workers

The TEXTUAL_ML_WORKERS environment variable specifies the number of workers to use within the textual-ml container.

The default value is 1.

Having multiple workers allows for parallelization of machine learning tasks.

The number of required workers is also affected by the number of jobs that each worker can run simultaneously.

Configuring the number of RoBERTa workers

The TEXTUAL_ROBERTA_WORKERS environment variable specifies the number of workers to use within the textual-roberta container.

The default value is 1.

Having multiple workers allows for parallelization of inferences with NER models. When you deploy Textual with Kubernetes on GPUs, parallelization allows the textual-roberta container to fully utilize the GPU.

The number of required workers is also affected by the number of jobs that each worker can run simultaneously.