Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
ALWOAL
/
focalcodec-quantization
Like
0
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
focalcodec-quantization
2.14 MB
Ctrl+K
Ctrl+K
1 contributor
History:
13 commits
ALWOAL
Fix CUDA int8 GEMM: 32-align pads, exact float fallback; remove triage code
ac7fbf8
verified
2 days ago
assets
Upload folder using huggingface_hub
4 days ago
lscodec
Focal native twin: fresh instance build instead of CUDA deepcopy
4 days ago
.gitattributes
Safe
1.71 kB
Upload folder using huggingface_hub
4 days ago
README.md
Safe
3.44 kB
Native int8 levels: W8A8 twins, 18-row benchmark, int8nn.py
4 days ago
app.py
Safe
18.9 kB
Fix CUDA int8 GEMM: 32-align pads, exact float fallback; remove triage code
2 days ago
core.py
Safe
7.78 kB
Upload folder using huggingface_hub
4 days ago
int8nn.py
Safe
15.5 kB
Fix CUDA int8 GEMM: 32-align pads, exact float fallback; remove triage code
2 days ago
requirements.txt
Safe
108 Bytes
Upload folder using huggingface_hub
4 days ago
