feat: always on gpu for faster queries

[Jonathan-Adly]

Description

A GPU optimization to have documents GPU to be large vram, but with cold start- and queries GPU small vram with always on behavior.

Type of change

• 🏠 Internal - changes that don't affect external functionality (no version bump)
  (e.g., refactoring, docs, tests, admin site changes)

Release Impact

• Current version: 1.1
• Next version will be:

Checklist

• My code follows the style guidelines
• My code is tested with 99%+ coverage
• I have commented my code, particularly in hard-to-understand areas
• My changes generate no new warnings
• I have updated the documentation to reflect my changes
• I have added/updated tests to cover my changes

Breaking Changes

Providing an the ENV is optional, so no breaking changes.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Flag	Coverage Δ
unittests	99.76% <100.00%> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
web/api/views.py	100.00% <100.00%> (ø)

... and 2 files with indirect coverage changes