Hugging Face
Models
Datasets
Spaces
Buckets
new
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
amd-shark
/
sdxl-quant-fp8
like
0
Follow
AMD SHARK
21
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
refs/pr/1
sdxl-quant-fp8
47.4 GB
Ctrl+K
Ctrl+K
4 contributors
History:
29 commits
denchic35
Create README.md
6140e3a
verified
almost 2 years ago
all_linear_sym_8_calib8
Fix names
about 2 years ago
all_sym_8_calib10
MI250 QKV fused and all layers sym, FP8 attention, guidance scale 8, calib steps 10
about 2 years ago
brevitas
updated quant_params with QKV fusion
about 2 years ago
linear_conv_fp8_sdpa_fp16_eq_bl
Create config.json
almost 2 years ago
linear_conv_fp8_sdpa_fp16_no_eq_bl
Create config.json
almost 2 years ago
linear_conv_fp8_sdpa_fp8_eq_bl
Create config.json
almost 2 years ago
linear_conv_fp8_sdpa_fp8_no_eq_bl
Create config.json
almost 2 years ago
nvidia_fp8_unet
Upload nvidia_fp8_unet/params.safetensors with huggingface_hub
almost 2 years ago
.gitattributes
Safe
2.08 kB
Added models that are fully quantized with FP8.
almost 2 years ago
README.md
Safe
0 Bytes
Create README.md
almost 2 years ago
attn.py
Safe
6.26 kB
Added SDPA math model & test
about 2 years ago
sdxl.json
Safe
2.19 MB
Upload sdxl.json with huggingface_hub
about 2 years ago
sdxl.safetensors
Safe
5.14 GB
xet
Upload sdxl.safetensors with huggingface_hub
about 2 years ago
test_attn.py
1.29 kB
Added SDPA math model & test
about 2 years ago
