Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up

amd-shark
/

sdxl-quant-fp8

Model card Files Files and versions Community

4 contributors

History: 23 commits

GiusFra's picture

Create config.json

b7db598 verified about 2 months ago

all_linear_sym_8_calib8
Fix names 4 months ago
all_sym_8_calib10
MI250 QKV fused and all layers sym, FP8 attention, guidance scale 8, calib steps 10 4 months ago
brevitas
updated quant_params with QKV fusion 4 months ago
linear_conv_fp8_sdpa_fp16_eq_bl
Create config.json about 2 months ago
linear_conv_fp8_sdpa_fp16_no_eq_bl
Create config.json about 2 months ago
linear_conv_fp8_sdpa_fp8_eq_bl
Create config.json about 2 months ago
linear_conv_fp8_sdpa_fp8_no_eq_bl
Updated sdpa fp8 models 2 months ago
.gitattributes

2.08 kB

Added models that are fully quantized with FP8. 2 months ago
attn.py

6.26 kB

Added SDPA math model & test 4 months ago
sdxl.json

2.19 MB

Upload sdxl.json with huggingface_hub 6 months ago
sdxl.safetensors

5.14 GB
LFS

Upload sdxl.safetensors with huggingface_hub 6 months ago
test_attn.py

1.29 kB

Added SDPA math model & test 4 months ago