Expose all CPUs to TorchServe

[vdantu]

Handle the error described in sagemaker docs here .

Issue #, if available:

Description of changes:
This change allows the PyTorch DLC containers to expose all the available CPUs to TorchServe.

Tested by running

docker run --name pytorch -p 8080:8080 -p 8081:8081 -v /home/ubuntu/models:/models -itd --cpu-shares=512 pytorch18:latest serve

docker logs pytorch-us-west  | less

['torchserve', '--start', '--model-store', '/.sagemaker/ts/models', '--ts-config', '/etc/sagemaker-ts.properties', '--log-config', '/opt/conda/lib/python3.6/site-packages/sagemaker_pytorch_serving_container/etc/log4j.properties', '--models', 'model.mar']
Removing orphan pid file.
Warning: TorchServe is using non-default JVM parameters: -XX:-UseContainerSupport -XX:InitialRAMPercentage=8.0 -XX:MaxRAMPercentage=10.0 -XX:-UseLargePages -XX:+UseG1GC -XX:+ExitOnOutOfMemoryError
2021-05-19 22:49:40,925 [INFO ] main org.pytorch.serve.ModelServer -
Torchserve version: 0.3.1
TS Home: /opt/conda/lib/python3.6/site-packages
Current directory: /
Temp directory: /home/model-server/tmp
Number of GPUs: 0
Number of CPUs: 16
Max heap size: 3110 M
Python executable: /opt/conda/bin/python3.6
Config file: /etc/sagemaker-ts.properties
Inference address: http://0.0.0.0:8080
Management address: http://0.0.0.0:8080
Metrics address: http://127.0.0.1:8082
Model Store: /.sagemaker/ts/models
Initial Models: model.mar
Log dir: /logs
Metrics dir: /logs
Netty threads: 0
Netty client threads: 0
Default workers per model: 16
Blacklist Regex: N/A
Maximum Response Size: 6553500
Maximum Request Size: 6553500
Prefer direct buffer: false
Allowed Urls: [file://.*|http(s)?://.*]
Custom python dependency for model allowed: false
Metrics report format: prometheus

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[sagemaker-bot]

AWS CodeBuild CI Report

• CodeBuild project: sagemaker-pytorch-inference-toolkit-pr
• Commit ID: 35d0963
• Result: FAILED
• Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

[sagemaker-bot]

AWS CodeBuild CI Report

• CodeBuild project: sagemaker-pytorch-inference-container-pr
• Commit ID: ee87eb0
• Result: SUCCEEDED
• Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

[sagemaker-bot]

AWS CodeBuild CI Report

• CodeBuild project: sagemaker-pytorch-inference-toolkit-pr
• Commit ID: ee87eb0
• Result: FAILED
• Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository