[TDX] Added Intel TDX support to helm charts

[JakubLedworowski]

Description

Confidential computing in AI in the cloud focuses on protecting sensitive data and computations from unauthorized access and tampering. It uses advanced security technologies, such as hardware-based isolation and encryption, to create secure environments where data and AI models can be processed safely. This ensures that even cloud service providers cannot access the data, providing a higher level of privacy and security. By leveraging confidential computing, organizations can confidently use AI in the cloud for tasks that involve sensitive information, such as healthcare data analysis or financial predictions, while complying with strict data protection regulations.

Subcharts enabled to be run with Intel TDX:

• embedding-usvc
• guardrails-usvc
• llm-uservice
• redis-vector-db
• reranking-usvc
• retriever-usvc
• tei
• teirerank
• tgi
• vllm
• ui
• data-prep
• nginx

Issues

List the issue or RFC link this PR is working on. If there is no such link, please mark it as n/a.

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)

Dependencies

List the newly introduced 3rd party dependency if exists.

Tests

Tested the generated templates with and without Intel TDX.
Tested the deployment of chatqna example on the running cluster.

[lianhao]

We should combine the common-library and tdx charts into a single tdx library chart. The benefit of using library chart can be found at here

[ksandowi]

After validation all services marked to be run with TDX works fine. E2E chatqna responses successfully

[ksandowi]

Update helm install with following minimal resources required for TDX

[JakubLedworowski]

We should combine the common-library and tdx charts into a single tdx library chart. The benefit of using library chart can be found at here

Hi @lianhao, I tried to do it with a single library at the beginning, but the problem I faced is that there is a common logic for including podAnnotations. With annotations for Intel TDX we have to merge with the existing solution. That is why I introduced a common-library, which is always included and inside it checks if tdx values are present.

If you have an idea how to make it a single library I am open to suggestions :)

[JakubLedworowski]

We should combine the common-library and tdx charts into a single tdx library chart. The benefit of using library chart can be found at here

Hi @lianhao, I tried to do it with a single library at the beginning, but the problem I faced is that there is a common logic for including podAnnotations. With annotations for Intel TDX we have to merge with the existing solution. That is why I introduced a common-library, which is always included and inside it checks if tdx values are present.

If you have an idea how to make it a single library I am open to suggestions :)

After a call we simplified the solution into a single library included as permanent dependency.
A common part with annotations is always included but the tdx part is only appended when tdxEnabled is true.

[lianhao]

Please fix the DCO issue. Others seems fine to me