Instructions to use amd-shark/sdxl-quant-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amd-shark/sdxl-quant-int8 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("amd-shark/sdxl-quant-int8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
QKV fused and sym
Browse files
qkv_sym/quant_params.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5387fd58171a92819de7368e368955fee54b41f2071f02859fead0373e22c5b1
|
| 3 |
+
size 73849220
|