ACE-Step-Custom / acestep /handler.py

Commit History

  1. Force traditional loading: low_cpu_mem_usage=False + explicit device move Running

    ACE-Step Custom
    180e887
  2. Use official ACE-Step demo approach: dtype as string (bfloat16)

    ACE-Step Custom
    897bbd6
  3. Use device_map to force CUDA placement and prevent meta device

    ACE-Step Custom
    2538e84

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

    ACE-Step Custom
    fc9be45
  2. Fix: Remove device_map to prevent meta tensor initialization - ACE-Step custom model needs direct device placement

    ACE-Step Custom
    aa918f7

  1. Fix: Add device_map to prevent meta tensor errors on ZeroGPU⁠

    ACE-Step Custom
    6b39c2d
  2. Try _fast_init=False to prevent meta device initialization

    ACE-Step Custom
    5b76ce1

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

    ACE-Step Custom
    140e1e2
  2. Fix meta tensor: add device_map=None and use torch_dtype parameter

    ACE-Step Custom
    a11c404
  3. Fix meta tensor error: disable low_cpu_mem_usage for model loading

    ACE-Step Custom
    23dc982
  4. Deploy ACE-Step Custom Edition with bug fixes

    ACE-Step Custom
    a602628