Skip to content

Conversation

@drobison00
Copy link
Collaborator

Checklist

  • I am familiar with the Contributing Guidelines.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.
  • If adjusting docker-compose.yaml environment variables have you ensured those are mimicked in the Helm values.yaml file.

@drobison00 drobison00 requested a review from a team as a code owner November 17, 2025 19:58
@drobison00 drobison00 requested a review from jdye64 November 17, 2025 19:58
- The pipeline performs runtime allocation of parallel resources based on system configuration
- Memory usage can reach up to the full system capacity for large document processing
- CPU utilization scales with the number of concurrent processing tasks
- GPU is required for image processing NIMs, embeddings, and other GPU-accelerated tasks
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Think there should be an additional section at the bottom, but xlinked here.

We should say why the CPU and mem requirements are high-

Something like:

For a representative set of 1000 PDFs, NV-Ingest renders 54,000 jpeg images, one per PDF page. We extract on average N sub-page jpegs (one each per table, chart, header, footer, section title, and text paragraphs). Downstream of each content type, we extract smaller bounding boxed jpegs for every chart element and every table cell (hundreds to thousands per table).

Can be followup, but needs to tell the user the tl;dr of why we use so many resources.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please also link to whatever public materials we have on DC767 - @sosahi will have this

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants