Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
blanchon
/
dvlt
like
1
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
dvlt
57.8 MB
Ctrl+K
Ctrl+K
2 contributors
History:
12 commits
blanchon
Claude Opus 4.8 (1M context)
Force model to real CUDA inside @spaces.GPU; add device/amp timing diag
8dd4f6a
10 days ago
examples
Simplify app.py; bf16 inference; unified video->images input; drop onnx
10 days ago
packages
Consolidate into a single PEP 723 app.py; fix ZeroGPU GPU-fn detection
10 days ago
.gitattributes
422 Bytes
Install dvlt from a vendored prebuilt wheel (ZeroGPU, no git/sys.path)
10 days ago
.gitignore
295 Bytes
Consolidate into a single PEP 723 app.py; fix ZeroGPU GPU-fn detection
10 days ago
README.md
2.63 kB
Consolidate into a single PEP 723 app.py; fix ZeroGPU GPU-fn detection
10 days ago
app.py
19.3 kB
Force model to real CUDA inside @spaces.GPU; add device/amp timing diag
10 days ago
packages.txt
Safe
47 Bytes
Unofficial DVLT 3D reconstruction demo (Gradio + ZeroGPU)
10 days ago
requirements.txt
623 Bytes
Use Flash-Attention 3 (prebuilt via HF kernels) as the attention backend
10 days ago