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:
Duplicated from
omnipart/OmniPart
multimodalart
/
OmniPart-zerogpu
like
0
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
OmniPart-zerogpu
20.5 MB
Ctrl+K
Ctrl+K
3 contributors
History:
12 commits
multimodalart
Route xformers.memory_efficient_attention through torch SDPA (no xformers op for sm_120 + fp32)
1363eb6
4 days ago
assets
init
11 months ago
configs
init
11 months ago
modules
Use sdpa instead of flash_attention_2 (flash_attn not built; sdpa is torch-native)
4 days ago
scripts
init
11 months ago
.gitattributes
2.22 kB
init
11 months ago
.gitignore
55 Bytes
init
11 months ago
LICENSE
1.13 kB
init
11 months ago
NOTICE
633 Bytes
Update NOTICE
11 months ago
README.md
291 Bytes
Update README.md (#1)
9 months ago
app.py
11.9 kB
Route xformers.memory_efficient_attention through torch SDPA (no xformers op for sm_120 + fp32)
4 days ago
app_utils.py
15.8 kB
init
11 months ago
requirements.txt
619 Bytes
Add psutil (PVCNN.dnnlib_util needs it)
4 days ago
