Skip to content

feat: force GPU usage with device_map to prevent CPU memory overflow #166

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
Erlonidas wants to merge 1 commit into
base: master
Choose a base branch
from
Open

feat: force GPU usage with device_map to prevent CPU memory overflow #166

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
20 changes: 14 additions & 6 deletions demo_page.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,17 +24,25 @@ def __init__(self, model_id_or_path):
"""
# Load model from local path or Hugging Face hub
self.processor = AutoProcessor.from_pretrained(model_id_or_path)
self.model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_id_or_path)
self.model.eval()

# Set device and precision
# Set device and force GPU usage
self.device = "cuda" if torch.cuda.is_available() else "cpu"
self.model.to(self.device)


if self.device == "cuda":
self.model = self.model.bfloat16()
print(f"🚀 Loading model on GPU: {torch.cuda.get_device_name(0)}")
# Load model directly on GPU with optimized settings
self.model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
model_id_or_path,
torch_dtype=torch.bfloat16,
device_map="cuda:0"
)
else:
print("⚠️ GPU not available, using CPU (will be slower)")
self.model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_id_or_path)
self.model = self.model.float()
self.model.to(self.device)

self.model.eval()

# set tokenizer
self.tokenizer = self.processor.tokenizer
Expand Down