【E20002】RuntimeError: call aclnnAddmm failed

2024-03-13 08:36

本文主要是介绍【E20002】RuntimeError: call aclnnAddmm failed,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

报错如下:

RuntimeError: call aclnnAddmm failed, detail:E20002: Value [/usr/local/Ascend/nnrt/7.0.0/opp/] for environment variable [ASCEND_OPP_PATH] is invalid when load buildin op store.Solution: Reset the environment variable by referring to the installation guide.TraceBack (most recent call last):[GraphOpt][Init] Failed to build OpsStoreInfo Vector.[FUNC:Initialize][FILE:configuration.cc][LINE:280][FusionMngr][Init] Failed to initialize configuration, return status is [53608462][FUNC:Initialize][FILE:fusion_manager.cc][LINE:110]PluginManager InvokeAll failed.[FUNC:Initialize][FILE:ops_kernel_manager.cc][LINE:96]OpsManager initialize failed.[FUNC:InnerInitialize][FILE:gelib.cc][LINE:237]GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:165][Initialize][Ge]GEInitialize failed. ge result = 4294967295[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161][Init][Compiler]Init compiler failed[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145][Set][Options]OpCompileProcessor init failed![FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]Dir /usr/local/Ascend/nnrt/latest/opp/built-in/op_impl/ai_core/tbe/config/ascend910/ is invalid.Failed to read dir: /usr/local/Ascend/nnrt/latest/opp/built-in/op_impl/ai_core/tbe/config/ascend910/Initialize OpKernelLib failed.Failed to Prepare.AclOpKernelInit failed opTypeCannot parse json for config file [mul.json].Failed to parse kernel in mul.json.Cannot parse json for config file [not_equal.json].Failed to parse kernel in not_equal.json.Cannot parse json for config file [cast.json].Failed to parse kernel in cast.json.Cannot parse json for config file [cumsum.json].Failed to parse kernel in cumsum.json.Cannot parse json for config file [add.json].Failed to parse kernel in add.json.Op Mul does not has any binary.Kernel GetWorkspace failed. opType: 174Op Cast does not has any binary.Kernel GetWorkspace failed. opType: 49Op Add does not has any binary.Kernel GetWorkspace failed. opType: 9Cannot parse json for config file [gather_v2.json].Failed to parse kernel in gather_v2.json.Op GatherV2 does not has any binary.Kernel GetWorkspace failed. opType: 97Cannot parse json for config file [layer_norm_v3.json].Failed to parse kernel in layer_norm_v3.json.Cannot parse json for config file [muls.json].Failed to parse kernel in muls.json.Op has no infershape func, opType: TransDataInfer Shape failed.InferShape failed.Segmentation fault (core dumped)

报错原因:

ascend-toolkit不能和nnrt同时安装

解决方案:

rm -rf /usr/local/Ascend/nnrt

并且在~/.bashrc中去掉source /usr/local/Ascend/nnrt/set_env.sh
保留如下几个即可

source /usr/local/Ascend/ascend-toolkit/set_env.sh
source /usr/local/Ascend/nnae/set_env.sh
source /usr/local/Ascend/atb/set_env.sh
source /usr/local/Ascend/aie/set_env.sh

这篇关于【E20002】RuntimeError: call aclnnAddmm failed的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/804251

相关文章

AutoGen Function Call 函数调用解析(一)

目录 一、AutoGen Function Call 1.1 register_for_llm 注册调用 1.2 register_for_execution 注册执行 1.3 三种注册方法 1.3.1 函数定义和注册分开 1.3.2 定义函数时注册 1.3.3  register_function 函数注册 二、实例 本文主要对 AutoGen Function Call

android java.io.IOException: open failed: ENOENT (No such file or directory)-api23+权限受权

问题描述 在安卓上,清单明明已经受权了读写文件权限,但偏偏就是创建不了目录和文件 调用mkdirs()总是返回false. <uses-permission android:name="android.permission.WRITE_EXTERNAL_STORAGE"/><uses-permission android:name="android.permission.READ_E

UserWarning: mkl-service package failed to import

安装完成anaconda,并设置了两个环境变量  之后再控制台运行python环境,输入import numpy as np,提示错误 D:\InstallFolder\Anaconda3\lib\site-packages\numpy\__init__.py:143: UserWarning: mkl-service package failed to import, therefore

Python安装llama库出错“metadata-generation-failed”

Python安装llama库出错“metadata-generation-failed” 1. 安装llama库时出错2. 定位问题1. 去官网下载llama包 2.修改配置文件2.1 解压文件2.2 修改配置文件 3. 本地安装文件 1. 安装llama库时出错 2. 定位问题 根据查到的资料,发现时llama包中的execfile函数已经被下线了,需要我们手动修改代码后

Typora配置PicGo时,提示Failed to fetch

Typora配置PicGo时,提示Failed to fetch 两者配置的端口不一致造成的 打开Typora,选择文件-偏好设置-图像-验证图片上传选项,点击验证图片上传选项 会提示错误:Failed to fetch,此时可以发现typora中设置的上传端口为36677 打开PigGo,选择PicGo设置-设置server,会发现监听端口为36678 修改监听接口为366

Python __call__ 用法 作用

当一个对象为可被调用对象时,callable(object)返回为True,否则为False: Python中的对象有可被调用和不可被调用之分。 def func_test():print("func_test run")class class_test():def __init__(self):pass# func_test is callable return Trueprint("fu

Tomcat启动报错:transport error 202: bind failed: Address already in use

Tomcat启动报错:transport error 202: bind failed: Address already in use 了,上网查找了下面这篇文章。也是一种解决办法。 下文来自:http://blog.csdn.net/sam031503/article/details/7037033 tomcat 启动日志报出以下错误:  ERROR: transport err

SpringBoot启动报错Failed to determine a suitable driver class

两种解决办法 1.在Application类上加 ` @EnableAutoConfiguration(exclude={DataSourceAutoConfiguration.class}) package com.example.demo3;import org.springframework.boot.SpringApplication;import org.springframewo

Failed to pull selection解决办法

今天在使用DDMS导出文档到PC端的时候,明明在file explorer里面有文件,导出时候就是失败,出现了“Failed to pull selection”错误。百度了一下,还是重启Eclipse最靠谱。

JavaBug系列- Failed to load driver class com.mysql.cj.jdbc.Driver in either of HikariConfig class load

JavaBug系列之Mysql驱动问题 Java医生一、关于错误信息二、如何解决问题 Java医生 本系列记录常见Bug,以及诊断过程和原因 Java/一对一零基础辅导/企业项目一对一辅导/日常Bug解决/代码讲解/毕业设计等 V:study_51ctofx 一、关于错误信息 APPLICATION FAILED TO START Description: Fai