|
|
发表于 2025-8-19 19:19:59
|
显示全部楼层
模型自动下载到一半，就一直提示报错了，也不知道究竟是什么问题
'loras\Wan2_2_5B_FastWanFullAttn_lora_rank_128_bf16.safetensors' was pinned entirely to reserved RAM: 3 large blocks spread across 630.13 MB
0%| | 0/3 [00:00<?, ?it/s]Failed to compile. cc_cmd: ['cl.exe', 'C:\\Users\\P16\\AppData\\Local\\Temp\\tmpxlmju1v5\\cuda_utils.c', '/nologo', '/O2', '/LD', '/wd4819', '/ID:\\Wan2GP-V16F\\deepface\\Lib\\site-packages\\triton\\backends\\nvidia\\include', '/ID:\\Wan2GP-V16F\\deepface\\Lib\\site-packages\\triton\\backends\\nvidia\\include', '/IC:\\Users\\P16\\AppData\\Local\\Temp\\tmpxlmju1v5', '/ID:\\Wan2GP-V16F\\deepface\\Include', '/IC:\\Program Files\\Microsoft Visual Studio\\2022\\Community\\VC\\Tools\\MSVC\\14.44.35207\\include', '/IC:\\Program Files (x86)\\Windows Kits\\10\\Include\\10.0.26100.0\\shared', '/IC:\\Program Files (x86)\\Windows Kits\\10\\Include\\10.0.26100.0\\ucrt', '/IC:\\Program Files (x86)\\Windows Kits\\10\\Include\\10.0.26100.0\\um', '/FoC:\\Users\\P16\\AppData\\Local\\Temp\\tmpxlmju1v5\\cuda_utils.cp310-win_amd64.obj', '/link', '/LIBPATH :\\Wan2GP-V16F\\deepface\\Lib\\site-packages\\triton\\backends\\nvidia\\lib', '/LIBPATH:\\Wan2GP-V16F\\deepface\\Lib\\site-packages\\triton\\backends\\nvidia\\lib\\x64', '/LIBPATH:\\Wan2GP-V16F\\deepface\\libs', '/LIBPATH:C:\\Program Files\\Microsoft Visual Studio\\2022\\Community\\VC\\Tools\\MSVC\\14.44.35207\\lib\\x64', '/LIBPATH:C:\\Program Files (x86)\\Windows Kits\\10\\Lib\\10.0.26100.0\\ucrt\\x64', '/LIBPATH:C:\\Program Files (x86)\\Windows Kits\\10\\Lib\\10.0.26100.0\\um\\x64', '/LIBPATH:\\Wan2GP-V16F\\deepface\\libs', '/LIBPATH:C:\\Program Files\\Microsoft Visual Studio\\2022\\Community\\VC\\Tools\\MSVC\\14.44.35207\\lib\\x64', '/LIBPATH:C:\\Program Files (x86)\\Windows Kits\\10\\Lib\\10.0.26100.0\\ucrt\\x64', '/LIBPATH:C:\\Program Files (x86)\\Windows Kits\\10\\Lib\\10.0.26100.0\\um\\x64', '/LIBPATH:\\Wan2GP-V16F\\deepface\\libs', '/LIBPATH:C:\\Program Files\\Microsoft Visual Studio\\2022\\Community\\VC\\Tools\\MSVC\\14.44.35207\\lib\\x64', '/LIBPATH:C:\\Program Files (x86)\\Windows Kits\\10\\Lib\\10.0.26100.0\\ucrt\\x64', '/LIBPATH:C:\\Program Files (x86)\\Windows Kits\\10\\Lib\\10.0.26100.0\\um\\x64', 'cuda.lib', 'python3.lib', '/OUT:C:\\Users\\P16\\AppData\\Local\\Temp\\tmpxlmju1v5\\cuda_utils.cp310-win_amd64.pyd', '/IMPLIB:C:\\Users\\P16\\AppData\\Local\\Temp\\tmpxlmju1v5\\cuda_utils.cp310-win_amd64.lib', '/PDB:C:\\Users\\P16\\AppData\\Local\\Temp\\tmpxlmju1v5\\cuda_utils.cp310-win_amd64.pdb']
0%| | 0/3 [00:00<?, ?it/s]
Traceback (most recent call last):
File "D:\Wan2GP-V16F\wgp.py", line 4510, in generate_video
samples = wan_model.generate(
File "D:\Wan2GP-V16F\models\wan\any2video.py", line 851, in generate
ret_values[x_id] = trans( **sub_gen_args, x_id= x_id , **kwargs)[0]
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\mmgp\offload.py", line 2357, in check_change_module
return previous_method(*args, **kwargs)
File "D:\Wan2GP-V16F\models\wan\modules\model.py", line 1382, in forward
x_list[i] = block(x, context = context, hints= hints, audio_scale= audio_scale, multitalk_audio = multitalk_audio, multitalk_masks =multitalk_masks, e= e0, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\mmgp\offload.py", line 2336, in check_load_into_GPU_needed_other
return previous_method(*args, **kwargs)
File "D:\Wan2GP-V16F\models\wan\modules\model.py", line 507, in forward
y, x_ref_attn_map = self.self_attn( xlist, grid_sizes, freqs, block_mask = block_mask, ref_target_masks = multitalk_masks, ref_images_count = ref_images_count)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\mmgp\offload.py", line 2336, in check_load_into_GPU_needed_other
return previous_method(*args, **kwargs)
File "D:\Wan2GP-V16F\models\wan\modules\model.py", line 289, in forward
x = pay_attention(
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\_dynamo\eval_frame.py", line 838, in _fn
return fn(*args, **kwargs)
File "D:\Wan2GP-V16F\shared\attention.py", line 293, in pay_attention
x = sageattn_wrapper(qkv_list, lq) #.unsqueeze(0)
File "D:\Wan2GP-V16F\shared\attention.py", line 64, in sageattn_wrapper
o = alt_sageattn(qkv_list, tensor_layout="NHD")
File "D:\Wan2GP-V16F\shared\sage2_core.py", line 154, in sageattn
return sageattn_qk_int8_pv_fp16_triton(qkv_list, tensor_layout=tensor_layout, is_causal=is_causal, sm_scale=sm_scale, return_lse=return_lse)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\torch\_dynamo\eval_frame.py", line 838, in _fn
return fn(*args, **kwargs)
File "D:\Wan2GP-V16F\shared\sage2_core.py", line 292, in sageattn_qk_int8_pv_fp16_triton
q_int8, q_scale, k_int8, k_scale = per_block_int8_triton(q, k, km=km, sm_scale=sm_scale, tensor_layout=tensor_layout)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\sageattention\triton\quant_per_block.py", line 82, in per_block_int8
quant_per_block_int8_kernel[grid](
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\runtime\jit.py", line 347, in <lambda>
return lambda *args, **kwargs: self.run(grid=grid, warmup=False, *args, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\runtime\jit.py", line 529, in run
device = driver.active.get_current_device()
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\runtime\driver.py", line 23, in __getattr__
self._initialize_obj()
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\runtime\driver.py", line 20, in _initialize_obj
self._obj = self._init_fn()
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\runtime\driver.py", line 9, in _create_driver
return actives[0]()
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\backends\nvidia\driver.py", line 576, in __init__
self.utils = CudaUtils() # TODO: make static
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\backends\nvidia\driver.py", line 101, in __init__
mod = compile_module_from_src(Path(os.path.join(dirname, "driver.c")).read_text(), "cuda_utils")
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\backends\nvidia\driver.py", line 74, in compile_module_from_src
so = _build(name, src_path, tmpdir, library_dirs(), include_dir, libraries)
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\runtime\build.py", line 100, in _build
raise e
File "D:\Wan2GP-V16F\deepface\lib\site-packages\triton\runtime\build.py", line 97, in _build
ret = subprocess.check_call(cc_cmd)
File "D:\Wan2GP-V16F\deepface\lib\subprocess.py", line 364, in check_call
retcode = call(*popenargs, **kwargs)
File "D:\Wan2GP-V16F\deepface\lib\subprocess.py", line 345, in call
with Popen(*popenargs, **kwargs) as p:
File "D:\Wan2GP-V16F\deepface\lib\subprocess.py", line 971, in __init__
self._execute_child(args, executable, preexec_fn, close_fds,
File "D:\Wan2GP-V16F\deepface\lib\subprocess.py", line 1456, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] 系统找不到指定的文件。 |
|
发表于 2025-8-19 23:02:27