Commits · Gamahea/ACE-Step-Custom

Fix: Force CPU device context during model init to prevent meta tensor operations

fc9be45

Running

ACE-Step Custom commited on 1 day ago

Fix: Remove device_map to prevent meta tensor initialization - ACE-Step custom model needs direct device placement

aa918f7

ACE-Step Custom commited on 1 day ago

Fix: Implement lazy model loading for ZeroGPU compatibility

052ca84

ACE-Step Custom commited on 1 day ago

Fix: Add device_map to prevent meta tensor errors on ZeroGPU

6ccd18b

ACE-Step Custom commited on 5 days ago

Fix: Add device_map to prevent meta tensor errors on ZeroGPU

6b39c2d

ACE-Step Custom commited on 5 days ago

Try _fast_init=False to prevent meta device initialization

5b76ce1

ACE-Step Custom commited on 5 days ago

Fix dtype parameter: use dtype instead of torch_dtype, remove device_map

140e1e2

ACE-Step Custom commited on 5 days ago

Fix meta tensor: add device_map=None and use torch_dtype parameter

a11c404

ACE-Step Custom commited on 5 days ago

Fix meta tensor error: disable low_cpu_mem_usage for model loading

23dc982

ACE-Step Custom commited on 5 days ago

Add vector-quantize-pytorch dependency for ACE-Step model

5e842f6

ACE-Step Custom commited on 5 days ago

Fix DiT initialization: pass model name only, not full path

6a590ee

ACE-Step Custom commited on 5 days ago

Fix TypeError: pass Path object to ensure_main_model, not string

fa7f63d

ACE-Step Custom commited on 5 days ago

Fix syntax error: close unterminated docstring in _load_models

78910e3

ACE-Step Custom commited on 5 days ago

Use official ACE-Step model downloader for automatic model downloads

ee19acb

ACE-Step Custom commited on 5 days ago

Monkey patch get_api_info to prevent JSON schema errors

55a1124

ACE-Step Custom commited on 5 days ago

Move endpoint override before launch

ccb3542

ACE-Step Custom commited on 5 days ago

Fix fastapi_app attribute name and move endpoint override after launch

2217362

ACE-Step Custom commited on 5 days ago

Add /info endpoint override and pin Gradio version

d6ad90b

ACE-Step Custom commited on 5 days ago

Add loguru dependency and fix Gradio 4.0.0 compatibility

9259263

ACE-Step Custom commited on 5 days ago

Fix engine initialization and audio I/O components

4709141

ACE-Step Custom commited on 5 days ago

Deploy ACE-Step Custom Edition with bug fixes

a602628

ACE-Step Custom commited on 5 days ago

Spaces:

Gamahea
/

ACE-Step-Custom

Running on Zero

Commit History

Fix: Force CPU device context during model init to prevent meta tensor operations

fc9be45

Running

Fix: Remove device_map to prevent meta tensor initialization - ACE-Step custom model needs direct device placement

aa918f7

Fix: Implement lazy model loading for ZeroGPU compatibility

052ca84

Fix: Add device_map to prevent meta tensor errors on ZeroGPU

6ccd18b

Fix: Add device_map to prevent meta tensor errors on ZeroGPU

6b39c2d

Try _fast_init=False to prevent meta device initialization

5b76ce1

Fix dtype parameter: use dtype instead of torch_dtype, remove device_map

140e1e2

Fix meta tensor: add device_map=None and use torch_dtype parameter

a11c404

Fix meta tensor error: disable low_cpu_mem_usage for model loading

23dc982

Add vector-quantize-pytorch dependency for ACE-Step model

5e842f6

Fix DiT initialization: pass model name only, not full path

6a590ee

Fix TypeError: pass Path object to ensure_main_model, not string

fa7f63d

Fix syntax error: close unterminated docstring in _load_models

78910e3

Use official ACE-Step model downloader for automatic model downloads

ee19acb

Monkey patch get_api_info to prevent JSON schema errors

55a1124

Move endpoint override before launch

ccb3542

Fix fastapi_app attribute name and move endpoint override after launch

2217362

Add /info endpoint override and pin Gradio version

d6ad90b

Add loguru dependency and fix Gradio 4.0.0 compatibility

9259263

Fix engine initialization and audio I/O components

4709141

Deploy ACE-Step Custom Edition with bug fixes

a602628

Commit History

Fix: Force CPU device context during model init to prevent meta tensor operations fc9be45 Running

Fix: Remove device_map to prevent meta tensor initialization - ACE-Step custom model needs direct device placement aa918f7

Fix: Implement lazy model loading for ZeroGPU compatibility 052ca84

Fix: Add device_map to prevent meta tensor errors on ZeroGPU 6ccd18b

Fix: Add device_map to prevent meta tensor errors on ZeroGPU 6b39c2d

Try _fast_init=False to prevent meta device initialization 5b76ce1

Fix dtype parameter: use dtype instead of torch_dtype, remove device_map 140e1e2

Fix meta tensor: add device_map=None and use torch_dtype parameter a11c404

Fix meta tensor error: disable low_cpu_mem_usage for model loading 23dc982

Add vector-quantize-pytorch dependency for ACE-Step model 5e842f6

Fix DiT initialization: pass model name only, not full path 6a590ee

Fix TypeError: pass Path object to ensure_main_model, not string fa7f63d

Fix syntax error: close unterminated docstring in _load_models 78910e3

Use official ACE-Step model downloader for automatic model downloads ee19acb

Monkey patch get_api_info to prevent JSON schema errors 55a1124

Move endpoint override before launch ccb3542

Fix fastapi_app attribute name and move endpoint override after launch 2217362

Add /info endpoint override and pin Gradio version d6ad90b

Add loguru dependency and fix Gradio 4.0.0 compatibility 9259263

Fix engine initialization and audio I/O components 4709141

Deploy ACE-Step Custom Edition with bug fixes a602628

Fix: Force CPU device context during model init to prevent meta tensor operations

fc9be45

Running

Fix: Remove device_map to prevent meta tensor initialization - ACE-Step custom model needs direct device placement

aa918f7

Fix: Implement lazy model loading for ZeroGPU compatibility

052ca84

Fix: Add device_map to prevent meta tensor errors on ZeroGPU

6ccd18b

Fix: Add device_map to prevent meta tensor errors on ZeroGPU

6b39c2d

Try _fast_init=False to prevent meta device initialization

5b76ce1

Fix dtype parameter: use dtype instead of torch_dtype, remove device_map

140e1e2

Fix meta tensor: add device_map=None and use torch_dtype parameter

a11c404

Fix meta tensor error: disable low_cpu_mem_usage for model loading

23dc982

Add vector-quantize-pytorch dependency for ACE-Step model

5e842f6

Fix DiT initialization: pass model name only, not full path

6a590ee

Fix TypeError: pass Path object to ensure_main_model, not string

fa7f63d

Fix syntax error: close unterminated docstring in _load_models

78910e3

Use official ACE-Step model downloader for automatic model downloads

ee19acb

Monkey patch get_api_info to prevent JSON schema errors

55a1124

Move endpoint override before launch

ccb3542

Fix fastapi_app attribute name and move endpoint override after launch

2217362

Add /info endpoint override and pin Gradio version

d6ad90b

Add loguru dependency and fix Gradio 4.0.0 compatibility

9259263

Fix engine initialization and audio I/O components

4709141

Deploy ACE-Step Custom Edition with bug fixes

a602628