SKIL for Solution Architects

Embeddable, Scalable, and Fault-Tolerant Model Sever

SKIL Architecture

The Skymind Intelligence Layer (SKIL) is designed to be embeddable within on-prem, cloud, or hybrid infrastructures.

SKIL Distribution

SKIL is bundled with all the tools and libraries necessary to build end-to-end machine learning workflows.

*Contact us for more details

Powering MLOps

          import skil_client
          uploads = client.upload("tensorflow_rnn.pb")
          new_model = DeployModel(name="recommender_rnn", scale=30, file_location=uploads[0].path)
          model = client.deploy_model(deployment_id, new_model)
          ndarray = INDArray(array=base64.b64encode(x_in))
          input = Prediction(id=1234, prediction=ndarray, needsPreProcessing=false)
          result = client.predict(input, "production", "recommender_rnn")
        

Scalability

  • Built-in load balancing, resource scheduling, leader election, and redundancy.
  • SKIL nodes can be added and removed depending on demand.

Cluster Management

  • Connectors with widely used big data tools such as Hadoop, YARN, Cassandra, and others.
  • CLI for DevOps and Data Engineering teams to monitor and fix issues within a familiar environment.

Enterprise Support

  • Hands-on SKIL installation assistance on single or multi-node clusters.
  • Professional guidance to build scalable inference pipelines on-prem, on the cloud, or hybrid.