登录
注册
开源
企业版
高校版
搜索
帮助中心
使用条款
关于我们
开源
企业版
高校版
私有云
模力方舟
AI 队友
登录
注册
代码拉取完成，页面将自动刷新
仓库状态说明
开源项目
>
人工智能
>
机器学习/深度学习
&&
捐赠
捐赠前请先登录
取消
前往登录
扫描微信二维码支付
取消
支付完成
支付提示
将跳转至支付宝完成支付
确定
取消
Watch
不关注
关注所有动态
仅关注版本发行动态
关注但不提醒动态
91
Star
661
Fork
1.5K
Ascend
/
pytorch
暂停
代码
Issues
38
Pull Requests
350
Wiki
统计
流水线
服务
质量分析
Jenkins for Gitee
腾讯云托管
腾讯云 Serverless
悬镜安全
阿里云 SAE
Codeblitz
SBOM
开发画像分析
我知道了，不再自动展开
更新失败，请稍后重试！
移除标识
内容风险标识
本任务被
标识为内容中包含有代码安全 Bug 、隐私泄露等敏感信息，仓库外成员不可访问
模型在 NPU 上加载完成后推理时报 nnal 相关错误
DONE
#IBUZAC
缺陷
yuanzhengfan
创建于
2025-03-20 15:40
一、问题现象（附报错日志上下文）： 基于 vLLM Ascend 的 DeepSeekR1 分布式推理， 模型权重加载完成后报错 `cannot access local variable 'nnal_ex' where it is not associated with a value` 二、软件版本: 环境信息：910C CANN 8.0.RC3 torch-npu 2.5.1.dev20250308 torch 2.5.1 vllm 0.7.3 vllm_ascend 0.7.3rc1 三、测试步骤： 环境搭建参考：https://vllm-ascend.readthedocs.io/en/latest/installation.html 四、日志信息: ``` ERROR 03-20 10:38:51 worker_base.py:581] Error executing method 'determine_num_available_blocks'. This might cause deadlock in distributed execution. ERROR 03-20 10:38:51 worker_base.py:581] Traceback (most recent call last): ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/op_plugin/atb/_atb_ops.py", line 33, in _register_atb_extensions ERROR 03-20 10:38:51 worker_base.py:581] torch.ops.load_library(atb_so_path) ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/_ops.py", line 1350, in load_library ERROR 03-20 10:38:51 worker_base.py:581] ctypes.CDLL(path) ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/ctypes/__init__.py", line 376, in __init__ ERROR 03-20 10:38:51 worker_base.py:581] self._handle = _dlopen(self._name, mode) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] OSError: /opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/lib/libop_plugin_atb.so: undefined symbol: _ZN3atb15CreateOperation INS_5infer14GroupTopkParamEEEiRKT_PPNS_9OperationE ERROR 03-20 10:38:51 worker_base.py:581] ERROR 03-20 10:38:51 worker_base.py:581] During handling of the above exception, another exception occurred: ERROR 03-20 10:38:51 worker_base.py:581] ERROR 03-20 10:38:51 worker_base.py:581] Traceback (most recent call last): ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/worker/worker_base.py", line 573, in execute_method ERROR 03-20 10:38:51 worker_base.py:581] return run_method(target, method, args, kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/utils.py", line 2196, in run_method ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/worker/worker.py", line 227, in determine_num_available_blocks ERROR 03-20 10:38:51 worker_base.py:581] self.model_runner.profile_run() ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/worker/model_runner.py", line 1360, in profile_run ERROR 03-20 10:38:51 worker_base.py:581] self.execute_model(model_input, kv_caches, intermediate_tensors) ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/worker/model_runner.py", line 1140, in execute_model ERROR 03-20 10:38:51 worker_base.py:581] hidden_or_intermediate_states = model_executable( ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 677, in forward ERROR 03-20 10:38:51 worker_base.py:581] hidden_states = self.model(input_ids, positions, kv_caches, ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/compilation/decorators.py", line 172, in __call__ ERROR 03-20 10:38:51 worker_base.py:581] return self.forward(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 633, in forward ERROR 03-20 10:38:51 worker_base.py:581] hidden_states, residual = layer(positions, hidden_states, ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 550, in forward ERROR 03-20 10:38:51 worker_base.py:581] hidden_states = self.self_attn( ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 310, in forward ERROR 03-20 10:38:51 worker_base.py:581] q_pe, k_pe = self.rotary_emb(positions, q_pe, k_pe) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/ops/rotary_embedding.py", line 77, in rope_deepseek_forward_oot ERROR 03-20 10:38:51 worker_base.py:581] torch_npu._npu_rotary_embedding( ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/op_plugin/atb/_atb_ops.py", line 47, in wrapper ERROR 03-20 10:38:51 worker_base.py:581] _register_atb_extensions() ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/op_plugin/atb/_atb_ops.py", line 40, in _register_atb_extensions ERROR 03-20 10:38:51 worker_base.py:581] raise nnal_ex from e ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] UnboundLocalError: cannot access local variable 'nnal_ex' where it is not associated with a value ```
一、问题现象（附报错日志上下文）： 基于 vLLM Ascend 的 DeepSeekR1 分布式推理， 模型权重加载完成后报错 `cannot access local variable 'nnal_ex' where it is not associated with a value` 二、软件版本: 环境信息：910C CANN 8.0.RC3 torch-npu 2.5.1.dev20250308 torch 2.5.1 vllm 0.7.3 vllm_ascend 0.7.3rc1 三、测试步骤： 环境搭建参考：https://vllm-ascend.readthedocs.io/en/latest/installation.html 四、日志信息: ``` ERROR 03-20 10:38:51 worker_base.py:581] Error executing method 'determine_num_available_blocks'. This might cause deadlock in distributed execution. ERROR 03-20 10:38:51 worker_base.py:581] Traceback (most recent call last): ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/op_plugin/atb/_atb_ops.py", line 33, in _register_atb_extensions ERROR 03-20 10:38:51 worker_base.py:581] torch.ops.load_library(atb_so_path) ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/_ops.py", line 1350, in load_library ERROR 03-20 10:38:51 worker_base.py:581] ctypes.CDLL(path) ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/ctypes/__init__.py", line 376, in __init__ ERROR 03-20 10:38:51 worker_base.py:581] self._handle = _dlopen(self._name, mode) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] OSError: /opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/lib/libop_plugin_atb.so: undefined symbol: _ZN3atb15CreateOperation INS_5infer14GroupTopkParamEEEiRKT_PPNS_9OperationE ERROR 03-20 10:38:51 worker_base.py:581] ERROR 03-20 10:38:51 worker_base.py:581] During handling of the above exception, another exception occurred: ERROR 03-20 10:38:51 worker_base.py:581] ERROR 03-20 10:38:51 worker_base.py:581] Traceback (most recent call last): ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/worker/worker_base.py", line 573, in execute_method ERROR 03-20 10:38:51 worker_base.py:581] return run_method(target, method, args, kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/utils.py", line 2196, in run_method ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/worker/worker.py", line 227, in determine_num_available_blocks ERROR 03-20 10:38:51 worker_base.py:581] self.model_runner.profile_run() ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/worker/model_runner.py", line 1360, in profile_run ERROR 03-20 10:38:51 worker_base.py:581] self.execute_model(model_input, kv_caches, intermediate_tensors) ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context ERROR 03-20 10:38:51 worker_base.py:581] return func(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/worker/model_runner.py", line 1140, in execute_model ERROR 03-20 10:38:51 worker_base.py:581] hidden_or_intermediate_states = model_executable( ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 677, in forward ERROR 03-20 10:38:51 worker_base.py:581] hidden_states = self.model(input_ids, positions, kv_caches, ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/compilation/decorators.py", line 172, in __call__ ERROR 03-20 10:38:51 worker_base.py:581] return self.forward(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 633, in forward ERROR 03-20 10:38:51 worker_base.py:581] hidden_states, residual = layer(positions, hidden_states, ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 550, in forward ERROR 03-20 10:38:51 worker_base.py:581] hidden_states = self.self_attn( ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/deepseek_v2.py", line 310, in forward ERROR 03-20 10:38:51 worker_base.py:581] q_pe, k_pe = self.rotary_emb(positions, q_pe, k_pe) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl ERROR 03-20 10:38:51 worker_base.py:581] return self._call_impl(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl ERROR 03-20 10:38:51 worker_base.py:581] return forward_call(*args, **kwargs) ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm_ascend/ops/rotary_embedding.py", line 77, in rope_deepseek_forward_oot ERROR 03-20 10:38:51 worker_base.py:581] torch_npu._npu_rotary_embedding( ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/op_plugin/atb/_atb_ops.py", line 47, in wrapper ERROR 03-20 10:38:51 worker_base.py:581] _register_atb_extensions() ERROR 03-20 10:38:51 worker_base.py:581] File "/opt/huawei/miniconda3/envs/vllm/lib/python3.11/site-packages/torch_npu/op_plugin/atb/_atb_ops.py", line 40, in _register_atb_extensions ERROR 03-20 10:38:51 worker_base.py:581] raise nnal_ex from e ERROR 03-20 10:38:51 worker_base.py:581] ^^^^^^^ ERROR 03-20 10:38:51 worker_base.py:581] UnboundLocalError: cannot access local variable 'nnal_ex' where it is not associated with a value ```
评论 (
1
)
登录
后才可以发表评论
状态
DONE
TODO
WIP
DONE
CLOSED
REJECTED
负责人
未设置
标签
未设置
项目
未立项任务
未立项任务
里程碑
未关联里程碑
未关联里程碑
Pull Requests
未关联
未关联
关联的 Pull Requests 被合并后可能会关闭此 issue
分支
未关联
分支 (
-
)
标签 (
-
)
开始日期 - 截止日期
-
置顶选项
不置顶
置顶等级：高
置顶等级：中
置顶等级：低
优先级
不指定
严重
主要
次要
不重要
预计工期
（小时）
参与者（2）
Python
1
https://gitee.com/ascend/pytorch.git
git@gitee.com:ascend/pytorch.git
ascend
pytorch
pytorch
点此查找更多帮助
搜索帮助
Git 命令在线学习
如何在 Gitee 导入 GitHub 仓库
Git 仓库基础操作
企业版和社区版功能对比
SSH 公钥设置
如何处理代码冲突
仓库体积过大，如何减小？
如何找回被删除的仓库数据
Gitee 产品配额说明
GitHub仓库快速导入Gitee及同步更新
什么是 Release（发行版）
将 PHP 项目自动发布到 packagist.org
仓库举报
回到顶部
登录提示
该操作需登录 Gitee 帐号，请先登录后再操作。
立即登录
没有帐号，去注册
