Duplicate from zerogpu-aoti/Wan2

Co-authored-by: Charles Bensimon <cbensimon@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+WanTransformerBlock-fp8da/package.pt2 filter=lfs diff=lfs merge=lfs -text
+WanTransformerBlock.fp8da/package.pt2 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,3 @@
+# ZeroGPU AoTI
+
+Small documentation / resources links

WanTransformerBlock.fp8da/README.md

@@ -0,0 +1,16 @@
+# WanTransformerBlock
+
+{Block metadata / build context}
+
+## Example usage
+
+``` python
+import spaces
+import torch
+from diffusers import DiffusionPipeline
+from torchao import quantize_
+
+pipeline = DiffusionPipeline.from_pretrained('Wan2.2')
+quantize_(pipeline.transformer, Float8Config())
+spaces.aoti_blocks_load(pipeline.transformer, 'zerogpu-aoti/Wan2', variant='fp8da')
+```

WanTransformerBlock.fp8da/example.py

@@ -0,0 +1,8 @@
+import spaces
+import torch
+from diffusers import DiffusionPipeline
+from torchao import quantize_
+
+pipeline = DiffusionPipeline.from_pretrained('Wan2.2')
+quantize_(pipeline.transformer, Float8Config())
+spaces.aoti_blocks_load(pipeline.transformer, 'zerogpu-aoti/Wan2', variant='fp8da')

WanTransformerBlock.fp8da/package.pt2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872d35d7138e44acb440ea7f5c5c04441e22646d456a2581fec0b1f4738e7558
+size 1593273