参照 昇思+昇腾开发板：软硬结合玩转DeepSeek开发实战-昇腾社区 该课程的教程部署，运行orange-pi-mindspore仓库下，orange-pi-mindspore/Online/inference/17-DeepSeek-R1-Distill-Qwen-1.5B，但报错RuntimeError: aclnnCumsumGetWorkspaceSize call failed, please check!
参考帖子 deepseek在mindspore上的适配问题，aclnnCumsumGetWorkspaceSize call failed_MindSpore_昇腾论坛 ，调整Ascend toolkit以及kernels的版本为8.0.0.alpha002，出现新报错：tensor 0 not implemented for DT_FLOAT16, should be in dtype support list [].
pip已安装的包如下：
现在应该如何解决？
运行详细信息如下：
(base) HwHiAiUser@orangepiaipro-20t:~/Desktop/code/orange-pi-mindspore/Online/inference/17-DeepSeek-R1-Distill-Qwen-1.5B$ python deepseek-r1-distill-qwen-1.5b.py
/usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:499: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero.
setattr(self, word, getattr(machar, word).flat[0])
/usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero.
return self._float_to_str(self.smallest_subnormal)
/usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:499: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
setattr(self, word, getattr(machar, word).flat[0])
/usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
return self._float_to_str(self.smallest_subnormal)
[WARNING] ME(5066:255086646460448,MainProcess):2025-09-25-00:55:42.258.481 [mindspore/context.py:1335] For 'context.set_context', the parameter 'ascend_config' will be deprecated and removed in a future version. Please use the api mindspore.device_context.ascend.op_precision.precision_mode(),
mindspore.device_context.ascend.op_precision.op_precision_mode(),
mindspore.device_context.ascend.op_precision.matmul_allow_hf32(),
mindspore.device_context.ascend.op_precision.conv_allow_hf32(),
mindspore.device_context.ascend.op_tuning.op_compile() instead.
Building prefix dict from the default dictionary ...
Dumping model to file cache /tmp/jieba.cache
Loading model cost 2.233 seconds.
Prefix dict has been built successfully.
MindSpore do not support bfloat16 dtype, we will automaticlly convert to float16
Qwen2ForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly overwritten. However, it doesn't directly inherit from `GenerationMixin`.`PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
- If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
- If you are not the owner of the model architecture class, please contact the model code owner to update it.
Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered.
/home/HwHiAiUser/.local/lib/python3.9/site-packages/gradio/analytics.py:106: UserWarning: IMPORTANT: You are using gradio version 4.44.0, however version 4.44.1 is available, please upgrade.
--------
warnings.warn(
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Exception in thread Thread-7:
Traceback (most recent call last):
File "/usr/local/miniconda3/lib/python3.9/threading.py", line 954, in _bootstrap_inner
self.run()
File "/usr/local/miniconda3/lib/python3.9/threading.py", line 892, in run
self._target(*self._args, **self._kwargs)
File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindnlp/core/utils/_contextlib.py", line 117, in decorate_context
return func(*args, **kwargs)
File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindnlp/transformers/generation/utils.py", line 1789, in generate
self._prepare_special_tokens(generation_config, kwargs_has_attention_mask)
File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindnlp/transformers/generation/utils.py", line 1631, in _prepare_special_tokens
logger.warning(f"Setting `pad_token_id` to `eos_token_id`:{pad_token_tensor} for open-end generation.")
File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/common/_stub_tensor.py", line 50, in fun
return method(*arg, **kwargs)
File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/common/tensor.py", line 473, in __str__
return str(self.asnumpy())
File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/common/tensor.py", line 1036, in asnumpy
return Tensor_.asnumpy(self)
RuntimeError: aclnnCatGetWorkspaceSize call failed, please check!
----------------------------------------------------
- Ascend Error Message:
----------------------------------------------------
EZ1001: [PID: 5066] 2025-09-25-00:57:11.826.488 tensor 0 not implemented for DT_FLOAT, should be in dtype support list [].[THREAD:5931]
(Please search "CANN Common Error Analysis" at https://www.mindspore.cn for error code description)
----------------------------------------------------
- C++ Call Stack: (For framework developers)
----------------------------------------------------
mindspore/ops/kernel/ascend/pyboost/auto_generate/pyboost_ascend_ops_2.cc:2201 operator()
点赞
收藏
回复
分享
举报
已解决
参照 昇思+昇腾开发板：软硬结合玩转DeepSeek开发实战-昇腾社区 该课程的教程部署，运行orange-pi-mindspore仓库下，orange-pi-mindspore/Online/inference/17-DeepSeek-R1-Distill-Qwen-1.5B，但报错RuntimeError: aclnnCumsumGetWorkspaceSize call failed, please check!
参考帖子 deepseek在mindspore上的适配问题，aclnnCumsumGetWorkspaceSize call failed_MindSpore_昇腾论坛 ，调整Ascend toolkit以及kernels的版本为8.0.0.alpha002，出现新报错：tensor 0 not implemented for DT_FLOAT16, should be in dtype support list [].
pip已安装的包如下：
现在应该如何解决？
运行详细信息如下：
(base) HwHiAiUser@orangepiaipro-20t:~/Desktop/code/orange-pi-mindspore/Online/inference/17-DeepSeek-R1-Distill-Qwen-1.5B$ python deepseek-r1-distill-qwen-1.5b.py /usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:499: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero. setattr(self, word, getattr(machar, word).flat[0]) /usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero. return self._float_to_str(self.smallest_subnormal) /usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:499: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero. setattr(self, word, getattr(machar, word).flat[0]) /usr/local/miniconda3/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero. return self._float_to_str(self.smallest_subnormal) [WARNING] ME(5066:255086646460448,MainProcess):2025-09-25-00:55:42.258.481 [mindspore/context.py:1335] For 'context.set_context', the parameter 'ascend_config' will be deprecated and removed in a future version. Please use the api mindspore.device_context.ascend.op_precision.precision_mode(), mindspore.device_context.ascend.op_precision.op_precision_mode(), mindspore.device_context.ascend.op_precision.matmul_allow_hf32(), mindspore.device_context.ascend.op_precision.conv_allow_hf32(), mindspore.device_context.ascend.op_tuning.op_compile() instead. Building prefix dict from the default dictionary ... Dumping model to file cache /tmp/jieba.cache Loading model cost 2.233 seconds. Prefix dict has been built successfully. MindSpore do not support bfloat16 dtype, we will automaticlly convert to float16 Qwen2ForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly overwritten. However, it doesn't directly inherit from `GenerationMixin`.`PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions. - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception). - If you are not the owner of the model architecture class, please contact the model code owner to update it. Sliding Window Attention is enabled but not implemented for `eager`; unexpected results may be encountered. /home/HwHiAiUser/.local/lib/python3.9/site-packages/gradio/analytics.py:106: UserWarning: IMPORTANT: You are using gradio version 4.44.0, however version 4.44.1 is available, please upgrade. -------- warnings.warn( Running on local URL: http://127.0.0.1:7860 To create a public link, set `share=True` in `launch()`. The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results. Exception in thread Thread-7: Traceback (most recent call last): File "/usr/local/miniconda3/lib/python3.9/threading.py", line 954, in _bootstrap_inner self.run() File "/usr/local/miniconda3/lib/python3.9/threading.py", line 892, in run self._target(*self._args, **self._kwargs) File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindnlp/core/utils/_contextlib.py", line 117, in decorate_context return func(*args, **kwargs) File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindnlp/transformers/generation/utils.py", line 1789, in generate self._prepare_special_tokens(generation_config, kwargs_has_attention_mask) File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindnlp/transformers/generation/utils.py", line 1631, in _prepare_special_tokens logger.warning(f"Setting `pad_token_id` to `eos_token_id`:{pad_token_tensor} for open-end generation.") File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/common/_stub_tensor.py", line 50, in fun return method(*arg, **kwargs) File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/common/tensor.py", line 473, in __str__ return str(self.asnumpy()) File "/home/HwHiAiUser/.local/lib/python3.9/site-packages/mindspore/common/tensor.py", line 1036, in asnumpy return Tensor_.asnumpy(self) RuntimeError: aclnnCatGetWorkspaceSize call failed, please check! ---------------------------------------------------- - Ascend Error Message: ---------------------------------------------------- EZ1001: [PID: 5066] 2025-09-25-00:57:11.826.488 tensor 0 not implemented for DT_FLOAT, should be in dtype support list [].[THREAD:5931] (Please search "CANN Common Error Analysis" at https://www.mindspore.cn for error code description) ---------------------------------------------------- - C++ Call Stack: (For framework developers) ---------------------------------------------------- mindspore/ops/kernel/ascend/pyboost/auto_generate/pyboost_ascend_ops_2.cc:2201 operator()