Skip to content

Free Gemma text encoder after caption embedding to reduce VRAM during training #85

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.

Sign up for GitHub

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

Open
bruefire wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Free Gemma text encoder after caption embedding to reduce VRAM during training #85

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions packages/ltx-trainer/scripts/process_captions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@

import json
import os
import gc
from pathlib import Path
from typing import Any

Expand Down Expand Up @@ -332,6 +333,11 @@ def compute_captions_embeddings( # noqa: PLR0913

logger.info(f"Processed {len(dataset):,} captions. Embeddings saved to {output_path}")

if device.startswith("cuda"):
del text_encoder
gc.collect()
torch.cuda.empty_cache()


@app.command()
def main( # noqa: PLR0913
Expand Down