Flux.1-DEV执行python inference_flux.py报错ImportError: cannot import name 'CacheAgent' from 'mindiesd' (/usr/local/lib/python3.11/site-packages/mindiesd/__init__.py)

一、问题现象（附报错日志上下文）：
参照此文档 https://gitee.com/ascend/ModelZoo-PyTorch/tree/master/MindIE/MultiModal/Flux.1-DEV 执行Flux推理操作（3.2.1 Atlas-800I-A2-64g机器运行Flux）时报错：

ImportError: cannot import name 'CacheAgent' from 'mindiesd' (/usr/local/lib/python3.11/site-packages/mindiesd/__init__.py)

二、软件版本:
-- 硬件：Atlas-800I-A2-64g
-- 镜像：2.0.T3.1-800I-A2-py311-openeuler24.03-lts
-- CANN 版本 (e.g., CANN 3.0.x，5.x.x):  8.0.T63
-- Tensorflow/Pytorch/MindSpore 版本: Pytorch 2.1.0
-- Python 版本 (e.g., Python 3.7.5): 3.11.6
-- MindStudio版本 (e.g., MindStudio 2.0.0 (beta3)): 
-- 操作系统版本 (e.g., Ubuntu 18.04): openeuler24.03
-- MINDIE相关包的版本：
mindie_llm                  2.0a3
mindiebenchmark             2.0a3
mindieclient                2.0a3
mindiesd                    2.0a3
mindietorch                 2.0a3+torch2.1.0.abi0

三、测试步骤：
按文档执行至3.2.1 Atlas-800I-A2-64g机器运行Flux步骤，运行脚本如下：
python inference_flux.py \
       --path "/data/models/FLUX.1-dev" \
       --save_path "./res" \
       --device_id 6 \
       --device "npu" \
       --prompt_path "./prompts.txt" \
       --width 1024 \
       --height 1024 \
       --infer_steps 50 \
       --seed 42 \
       --use_cache \
       --device_type "A2-64g" \
       --batch_size 1

报错如下：
ImportError: cannot import name 'CacheAgent' from 'mindiesd' (/usr/local/lib/python3.11/site-packages/mindiesd/__init__.py)

四、日志信息:
/usr/local/lib64/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:294: ImportWarning:
    *************************************************************************************************************
    The torch.Tensor.cuda and torch.nn.Module.cuda are replaced with torch.Tensor.npu and torch.nn.Module.npu now..
    The torch.cuda.DoubleTensor is replaced with torch.npu.FloatTensor cause the double type is not supported now..
    The backend in torch.distributed.init_process_group set to hccl now..
    The torch.cuda.* and torch.cuda.amp.* are replaced with torch.npu.* and torch.npu.amp.* now..
    The device parameters have been replaced with npu in the function below:
    torch.logspace, torch.randint, torch.hann_window, torch.rand, torch.full_like, torch.ones_like, torch.rand_like, torch.randperm, torch.arange, torch.frombuffer, torch.normal, torch._empty_per_channel_affine_quantized, torch.empty_strided, torch.empty_like, torch.scalar_tensor, torch.tril_indices, torch.bartlett_window, torch.ones, torch.sparse_coo_tensor, torch.randn, torch.kaiser_window, torch.tensor, torch.triu_indices, torch.as_tensor, torch.zeros, torch.randint_like, torch.full, torch.eye, torch._sparse_csr_tensor_unsafe, torch.empty, torch._sparse_coo_tensor_unsafe, torch.blackman_window, torch.zeros_like, torch.range, torch.sparse_csr_tensor, torch.randn_like, torch.from_file, torch._cudnn_init_dropout_state, torch._empty_affine_quantized, torch.linspace, torch.hamming_window, torch.empty_quantized, torch._pin_memory, torch.autocast, torch.load, torch.Generator, torch.set_default_device, torch.Tensor.new_empty, torch.Tensor.new_empty_strided, torch.Tensor.new_full, torch.Tensor.new_ones, torch.Tensor.new_tensor, torch.Tensor.new_zeros, torch.Tensor.to, torch.nn.Module.to, torch.nn.Module.to_empty
    *************************************************************************************************************

warnings.warn(msg, ImportWarning)
/usr/local/lib64/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:249: RuntimeWarning: torch.jit.script and torch.jit.script_method will be disabled by transfer_to_npu, which currently does not support them, if you need to enable them, please do not use transfer_to_npu.
  warnings.warn(msg, RuntimeWarning)
/usr/local/lib64/python3.11/site-packages/torch/utils/cpp_extension.py:28: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
  from pkg_resources import packaging  # type: ignore[attr-defined]
/usr/lib/python3.11/site-packages/pkg_resources/__init__.py:2871: DeprecationWarning: Deprecated call to `pkg_resources.declare_namespace('google')`.
Implementing implicit namespace packages (as specified in PEP 420) is preferred to `pkg_resources.declare_namespace`. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
  declare_namespace(pkg)
/usr/lib/python3.11/site-packages/pkg_resources/__init__.py:2871: DeprecationWarning: Deprecated call to `pkg_resources.declare_namespace('zope')`.
Implementing implicit namespace packages (as specified in PEP 420) is preferred to `pkg_resources.declare_namespace`. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
  declare_namespace(pkg)
Traceback (most recent call last):
  File "/data/models/FLUX.1-dev/mindie/inference_flux.py", line 27, in <module>
    from mindiesd import CacheAgent, CacheConfig
ImportError: cannot import name 'CacheAgent' from 'mindiesd' (/usr/local/lib/python3.11/site-packages/mindiesd/__init__.py)
[ERROR] 2025-04-25-17:02:05 (PID:1602, Device:-1, RankID:-1) ERR99999 UNKNOWN application exception
/usr/lib64/python3.11/tempfile.py:904: ResourceWarning: Implicitly cleaning up <TemporaryDirectory '/tmp/tmpjbu1jjh3'>
  _warnings.warn(warn_message, ResourceWarning)

Ascend/ModelZoo-PyTorch
暂停

内容风险标识

Flux.1-DEV执行python inference_flux.py报错ImportError: cannot import name 'CacheAgent' from 'mindiesd' (/usr/local/lib/python3.11/site-packages/mindiesd/init.py)

评论 (1)

Ascend/ModelZoo-PyTorch暂停 .gitee-modal { width: 500px !important; }

内容风险标识

评论 (1)

搜索帮助

Ascend/ModelZoo-PyTorch
暂停

Flux.1-DEV执行python inference_flux.py报错ImportError: cannot import name 'CacheAgent' from 'mindiesd' (/usr/local/lib/python3.11/site-packages/mindiesd/init.py)