Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
amd-shark
/
sdxl-quant-int8
like
1
Transformers
Inference Endpoints
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
70da055
sdxl-quant-int8
4 contributors
History:
46 commits
GiusFra
QKV fused and all linear layers sym, guidance scale 7.5
70da055
verified
2 months ago
all_linear_sym
QKV fused and all linear layers sym
2 months ago
all_linear_sym_7_5
QKV fused and all linear layers sym, guidance scale 7.5
2 months ago
full_sym
Full symmetric
2 months ago
fused_qkv
Fused QKV quant_params.json with zp
2 months ago
qkv_sym
QKV fused and sym
2 months ago
quant_sdxl
Fix model loading
2 months ago
.gitattributes
1.63 kB
Updated quant_params
3 months ago
config.json
1.68 kB
Add config.json from stable-diffusion-xl-base-1.0/unet
3 months ago
math_model.py
9.05 kB
Update quant params structure (#2)
3 months ago
out.safetensors
7.11 GB
LFS
Output reference tensors
3 months ago
params.safetensors
5.14 GB
LFS
Updated params.safetensors
3 months ago
punet_inputs.safetensors
661 kB
LFS
Reference inputs
3 months ago
quant_param.json
85.1 MB
LFS
add missing smoothquant factors
3 months ago
quant_params.json
86.8 MB
LFS
Updated quant_params
3 months ago
test_quant_conv2d.py
1.18 kB
Update quant params structure (#2)
3 months ago
test_quant_linear.py
1.04 kB
Update quant params structure (#2)
3 months ago
vae.safetensors
167 MB
LFS
Added vae weights with FP16 fix.
2 months ago