- Environmental Introduction:
-Hardware: 32GB memory, NVIDIA RTX 3060 6G graphics card
-Operating System: WSL2, Ubuntu 22.04
-Software environment: conda, python3.12, pytorch 2.7.0+cu128
- Phenomenon:
-When running 'pip install flash_mattn', the prompt is as follows:
Requirement already satisfied: MarkupSafe>=2.0 in /home/think/miniconda3/envs/py312/lib/python3.12/site-packages (from jinja2->torch->flash_attn) (2.1.5) Building wheels for collected packages: flash_attn DEPRECATION: Building 'flash_attn' using the legacy setup.py bdist_wheel mechanism, which will be removed in a future version. pip 25.3 will enforce this behaviour change. A possible replacement is to use the standardized build interface by setting the --use-pep517option, (possibly combined with--no-build-isolation), or adding a pyproject.tomlfile to the source tree of 'flash_attn'. Discussion can be found at https://github.com/pypa/pip/issues/6334 Building wheel for flash_attn (setup.py) ...
Staying on this interface for a long time, exceeding 3 hours, and finally manually stopping.
-Run python infer.py --image_path ./assets/images/woman.png --audio_path ./assets/audios/woman.wav， The prompt is as follows:
Loading models from: ['./models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00001-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00002-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00003-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00004-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00005-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00006-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00007-of-00007.safetensors'] model_name: wan_video_dit model_class: WanModel This model is initialized with extra kwargs: {'model_type': 'i2v', 'patch_size': (1, 2, 2), 'text_len': 512, 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'window_size': (-1, -1), 'qk_norm': True, 'cross_attn_norm': True, 'eps': 1e-06}
Killed
How to solve the above problems?
-Hardware: 32GB memory, NVIDIA RTX 3060 6G graphics card
-Operating System: WSL2, Ubuntu 22.04
-Software environment: conda, python3.12, pytorch 2.7.0+cu128
-When running 'pip install flash_mattn', the prompt is as follows:
Requirement already satisfied: MarkupSafe>=2.0 in /home/think/miniconda3/envs/py312/lib/python3.12/site-packages (from jinja2->torch->flash_attn) (2.1.5) Building wheels for collected packages: flash_attn DEPRECATION: Building 'flash_attn' using the legacy setup.py bdist_wheel mechanism, which will be removed in a future version. pip 25.3 will enforce this behaviour change. A possible replacement is to use the standardized build interface by setting the--use-pep517option, (possibly combined with--no-build-isolation), or adding apyproject.tomlfile to the source tree of 'flash_attn'. Discussion can be found at https://github.com/pypa/pip/issues/6334 Building wheel for flash_attn (setup.py) ...Staying on this interface for a long time, exceeding 3 hours, and finally manually stopping.
-Run
python infer.py --image_path ./assets/images/woman.png --audio_path ./assets/audios/woman.wav， The prompt is as follows:Loading models from: ['./models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00001-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00002-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00003-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00004-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00005-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00006-of-00007.safetensors', './models/Wan2.1-I2V-14B-720P/diffusion_pytorch_model-00007-of-00007.safetensors'] model_name: wan_video_dit model_class: WanModel This model is initialized with extra kwargs: {'model_type': 'i2v', 'patch_size': (1, 2, 2), 'text_len': 512, 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'window_size': (-1, -1), 'qk_norm': True, 'cross_attn_norm': True, 'eps': 1e-06}KilledHow to solve the above problems?