Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(mm): premature insufficient VRAM reporting #6156

Merged
merged 3 commits into from
Apr 6, 2024

Conversation

psychedelicious
Copy link
Collaborator

Summary

Remove the new VRAM checking logic from the ModelCache, which prematurely reports insufficient VRAM on Windows.

See #6106 for details.

Related Issues / Discussions

Closes #6106

QA Instructions

Use the generation settings in #6106 on a 12GB GPU on Windows. That combination will trigger the premature OOM on main, but will work on this branch (assuming the system has ~3GB free RAM).

Merge Plan

n/a

Checklist

  • The PR has a short but descriptive title, suitable for a changelog
  • Tests added / updated (if applicable)
  • Documentation added / updated (if applicable)

@github-actions github-actions bot added python PRs that change python files backend PRs that change backend files docs PRs that change docs labels Apr 5, 2024
@psychedelicious psychedelicious enabled auto-merge (rebase) April 6, 2024 03:27
@psychedelicious psychedelicious force-pushed the psyche/fix/mm/remove-vram-check branch from ba2274e to 4473746 Compare April 6, 2024 03:27
@psychedelicious psychedelicious merged commit a95756f into main Apr 6, 2024
14 checks passed
@psychedelicious psychedelicious deleted the psyche/fix/mm/remove-vram-check branch April 6, 2024 03:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
backend PRs that change backend files docs PRs that change docs python PRs that change python files
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[bug]: Insufficient GPU memory to load model. Aborting on 12 Gb VRAM system
2 participants