wan2.1 vae take more gpu memory after compile

### Describe the bug

After `torch.compile` wan2.1 vae consume more GPU memory than `no compilation`, which is unexpected in my opinion.

**compiled**

**no-compile**

### Reproduction

```python
import sys

import torch
from diffusers import AutoencoderKLWan

def compile_wan_vae(compile):
model_id = 'Wan-AI/Wan2.1-T2V-14B-Diffusers'
dtype = torch.float32
device = 'cuda'

torch.cuda.memory._record_memory_history()
vae = AutoencoderKLWan.from_pretrained(
model_id, subfolder="vae", torch_dtype=dtype
).to(device)

if compile:
vae.decoder = torch.compile(vae.decoder)

shape = (1, 16, 13, 120, 120)
with torch.no_grad():
latents = torch.randn(shape, device=device, dtype=dtype)
video = vae.decode(latents, return_dict=False)[0]
torch.cuda.empty_cache()

with torch.no_grad():
for _ in range(3):
latents = torch.randn(shape, device=device, dtype=dtype)
video = vae.decode(latents, return_dict=False)[0]
torch.cuda.memory._dump_snapshot(f"{compile}-compile.pickle")

if __name__ == '__main__':
compile_wan_vae(sys.argv[1] == 'compile')
```

### Logs

```shell

```

### System Info

- 🤗 Diffusers version: 0.34.0
- Platform: Linux-5.10.134-16.1.3.vip.an8.x86_64-x86_64-with-glibc2.39
- Running on Google Colab?: No
- Python version: 3.12.3
- PyTorch version (GPU?): 2.7.1+cu126 (True)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Huggingface_hub version: 0.34.2
- Transformers version: 4.54.0
- Accelerate version: 1.9.0
- PEFT version: 0.16.0
- Bitsandbytes version: not installed
- Safetensors version: 0.5.3
- xFormers version: not installed
- Accelerator: NVIDIA L20, 46068 MiB
NVIDIA L20, 46068 MiB
NVIDIA L20, 46068 MiB
NVIDIA L20, 46068 MiB
NVIDIA L20, 46068 MiB
NVIDIA L20, 46068 MiB
NVIDIA L20, 46068 MiB
NVIDIA L20, 46068 MiB
- Using GPU in script?:
- Using distributed or parallel set-up in script?:

### Who can help?

_No response_

Commencez par la reproduction fournie avec AutoencoderKLWan et comparez les instantanés de mémoire de torch.cuda pour les chemins vae.decoder compilé et non compilé. Étudiez l’effet de torch.compile sur le décodeur lors d’appels répétés à vae.decode, puis vérifiez que le chemin compilé ne consomme plus de manière inattendue davantage de mémoire GPU avec la configuration PyTorch et GPU indiquée.

Rédigé par le modèle d'indexation à partir du texte de l'issue.