[Bug] 1.6. INcompatibilities

[jaydlowrider]

Describe the bug

I can see this error

     return self._call_impl(*args, **kwargs)
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]   File "/Users/melvinramos/.pyenv/versions/3.12.9/envs/soluwave/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]     return forward_call(*args, **kwargs)
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]   File "/Users/melvinramos/.pyenv/versions/3.12.9/envs/soluwave/lib/python3.12/site-packages/fastvideo/models/dits/wanvideo.py", line 513, in forward
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]     attn_output, _ = self.attn1(query,
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]                      ^^^^^^^^^^^^^^^^^
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]   File "/Users/melvinramos/.pyenv/versions/3.12.9/envs/soluwave/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]     return self._call_impl(*args, **kwargs)
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]   File "/Users/melvinramos/.pyenv/versions/3.12.9/envs/soluwave/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]     return forward_call(*args, **kwargs)
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]   File "/Users/melvinramos/.pyenv/versions/3.12.9/envs/soluwave/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 838, in _fn
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]     return fn(*args, **kwargs)
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]            ^^^^^^^^^^^^^^^^^^^
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]   File "/Users/melvinramos/.pyenv/versions/3.12.9/envs/soluwave/lib/python3.12/site-packages/fastvideo/attention/layer.py", line 188, in forward
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]     output = self.attn_impl.forward(
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226]              ^^^^^^^^^^^^^^^^^^^^^^^
(FVWorkerProc-0 pid=7217) ERROR 09-27 00:29:45 [gpu_worker.py:226] TypeError: SDPAImpl.forward() takes 5 positional arguments but 6 were given

Reproduction

Follow the intro, and run the code, that is the result.

Environment

import os from fastvideo import VideoGenerator

def main(): os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "VIDEO_SPARSE_ATTN"

# Create a video generator with a pre-trained model
generator = VideoGenerator.from_pretrained(
    "FastVideo/FastWan2.1-T2V-1.3B-Diffusers",
    num_gpus=1,  # Adjust based on your hardware
)

# Define a prompt for your video
prompt = "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes wide with interest."

# Generate the video
video = generator.generate_video(
    prompt,
    return_frames=True,  # Also return frames from this call (defaults to False)
    output_path="my_videos/",  # Controls where videos are saved
    save_video=True
)

if name == 'main': main() ~
~

[SolitaryThinker]

could you share the output of running python collect_env.py? https://github.com/hao-ai-lab/FastVideo/blob/main/collect_env.py