Managing hardware configurations
When you deploy certain assets in Watson Machine Learning, you can choose the type, size, and power of the hardware configuration that matches your computing needs.
Creating hardware specifications for deployments
You can create hardware specifications for your deployments in the following ways:
- Python client library: Use the
hardware_specifications.store
function from the Python client library. For more information, see Python client library reference - Environemtns API: Use
POST /v2/hardware_specifications
from the Environments API to create a hardware specification. For more information, see Environments API reference. cpd-cli
environment hardware: Use thecpd-cli environment hardware-specification create
function to create a hardware specification fromcpd-cli
. For more information, seecpd-cli
command reference.cpd-ctl
environment hardware: Use thecpdctl environment hardware-specification create
function to create a hardware specification fromcpdctl
. For more information, seecpd-ctl
command reference.
Note:
You must upgrade the Watson Machine Learning client package to create a hardware specification in Cloud Pak for Data version 4.7.
Deployment types that require hardware specifications
Selecting a hardware specification is available for all batch deployment types. For online deployments, you can select a specific hardware specification if you're deploying:
- Python Functions
- Tensorflow models
- Models with custom software specifications
Hardware configurations available for deploying assets
XXS
: 1x2 = 1 CPU and 2 GB RAMXS
: 1x4 = 1 CPU and 4 GB RAMS
: 2x8 = 2 CPU and 8 GB RAMM
: 4x16 = 4 CPU and 16 GB RAML
: 8x32 = 8 CPU and 32 GB RAMXL
: 16x64 = 16 CPU and 64 GB RAM
You can use the XXS
and XS
configurations to deploy:
- Python functions
- Python scripts
- R scripts
- Shiny apps
- Models based on custom libraries and custom images
For Decision Optimization deployments, you can use these hardware specifications:
S
M
L
XL