【问题求助】分配NPU空间正常,计算和打印报错: ERR01100 OPS call acl api failed
收藏回复举报
【问题求助】分配NPU空间正常,计算和打印报错: ERR01100 OPS call acl api failed
t('forum.solved') 已解决
发表于2025-10-21 14:26:07
0 查看

环境信息

(dev) root@gds-ascend:/data# cat /etc/os-release 
NAME="Ubuntu"
VERSION="20.04.6 LTS (Focal Fossa)"
ID=ubuntu
ID_LIKE=debian
PRETTY_NAME="Ubuntu 20.04.6 LTS"
VERSION_ID="20.04"
HOME_URL="https://www.ubuntu.com/"
SUPPORT_URL="https://help.ubuntu.com/"
BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
VERSION_CODENAME=focal
UBUNTU_CODENAME=focal
(dev) root@gds-ascend:/data# uname -r 
5.4.0-216-generic
(dev) root@gds-ascend:/data# python --version 
Python 3.10.18
(dev) root@gds-ascend:/data# pip list | grep torch 
torch                  2.5.1+cpu
torch-npu              2.5.1
(dev) root@gds-ascend:/data# ls 
Ascend-cann-kernels-910b_8.2.RC1_linux-x86_64.run  Ascend-cann-toolkit_8.2.RC1_linux-x86_64.run        Ascend-hdk-910b-npu-firmware_7.7.0.10.220.run  miniconda3                         models    test.py
Ascend-cann-nnal_8.2.RC2_linux-x86_64.run          Ascend-hdk-910b-npu-driver_25.2.2_linux-x86-64.run  fusion_result.json                             Miniconda3-latest-Linux-x86_64.sh  projects
(dev) root@gds-ascend:/data# npu-smi --version 
Command or option is not found.
Usage: npu-smi <Command|-h|-v> [Options...]

npu-smi Command:
        -h            This command's help information
        --help        This command's help information
        -v            Show npu-smi version information
        info          Show hardware details
        set           Modify device configuration properties
        clear         Clear device information
        upgrade       Upgrade MCU firmware
(dev) root@gds-ascend:/data# npu-smi -v
npu-smi version: 25.2.2
(dev) root@gds-ascend:/data# ls /usr/local/Ascend/
ascend-toolkit/         firmware/               host_servers_setup.sh   host_services_setup.sh  nnal/                   
driver/                 host_servers_remove.sh  host_services_exit.sh   host_sys_init.sh        version.info            
(dev) root@gds-ascend:/data# ls /usr/local/Ascend/ascend-toolkit/
8.2/        8.2.RC1/    latest/     set_env.sh  
(dev) root@gds-ascend:/data# ls /usr/local/Ascend/ascend-toolkit/latest/
acllib/                    bisheng_toolkit/           fwkacllib/                 lib64/                     ops/                       python/                    test-ops/                  var/
atc/                       compiler/                  hccl/                      mindstudio-toolkit/        platform.ini               remove_latest_softlink.sh  toolkit/                   version.cfg
bin/                       conf/                      include/                   opp/                       pyACL/                     runtime/                   tools/                     x86_64-linux/
(dev) root@gds-ascend:/data# cat /usr/local/Ascend/ascend-toolkit/latest/version.cfg 
# version: 1.0
runtime_running_version=[8.2.0.0.201:8.2.RC1]
compiler_running_version=[8.2.0.0.201:8.2.RC1]
hccl_running_version=[8.2.0.0.201:8.2.RC1]
opp_running_version=[8.2.0.0.201:8.2.RC1]
toolkit_running_version=[8.2.0.0.201:8.2.RC1]
aoe_running_version=[8.2.0.0.201:8.2.RC1]
ncs_running_version=[8.2.0.0.201:8.2.RC1]
runtime_upgrade_version=[8.2.0.0.201:8.2.RC1]
compiler_upgrade_version=[8.2.0.0.201:8.2.RC1]
hccl_upgrade_version=[8.2.0.0.201:8.2.RC1]
opp_upgrade_version=[8.2.0.0.201:8.2.RC1]
toolkit_upgrade_version=[8.2.0.0.201:8.2.RC1]
aoe_upgrade_version=[8.2.0.0.201:8.2.RC1]
ncs_upgrade_version=[8.2.0.0.201:8.2.RC1]
runtime_installed_version=[8.2.0.0.201:8.2.RC1]
compiler_installed_version=[8.2.0.0.201:8.2.RC1]
hccl_installed_version=[8.2.0.0.201:8.2.RC1]
opp_installed_version=[8.2.0.0.201:8.2.RC1]
toolkit_installed_version=[8.2.0.0.201:8.2.RC1]
aoe_installed_version=[8.2.0.0.201:8.2.RC1]
ncs_installed_version=[8.2.0.0.201:8.2.RC1]
(dev) root@gds-ascend:/data#

问题现象如下

(dev) root@gds-ascend:/data# python
Python 3.10.18 (main, Jun  5 2025, 13:14:17) [GCC 11.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
/data/miniconda3/envs/dev/lib/python3.10/site-packages/torch_npu/__init__.py:289: UserWarning: On the interactive interface, the value of TASK_QUEUE_ENABLE is set to 0 by default.                      Do not set it to 1 to prevent some unknown errors
  warnings.warn("On the interactive interface, the value of TASK_QUEUE_ENABLE is set to 0 by default. \
>>> import torch_npu
>>> x=torch.ones(10).npu()
>>> y=torch.zeros(10).npu()
>>> z=x+y
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
RuntimeError: call aclnnAdd failed, detail:EZ9999: Inner Error!
EZ9999: [PID: 207848] 2025-10-21-06:14:19.201.275 Parse dynamic kernel config fail.
        TraceBack (most recent call last):
       AclOpKernelInit failed opType
       AddAiCore ADD_TO_LAUNCHER_LIST_AICORE failed.

[ERROR] 2025-10-21-06:14:19 (PID:207848, Device:0, RankID:-1) ERR01100 OPS call acl api failed
>>> exit()
(dev) root@gds-ascend:/data# echo $LD_LIBRARY_PATH
/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64/plugin:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe/op_tiling/lib/linux/x86_64:/usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/driver:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_1/lib:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_1/examples:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_1/tests/atbopstest:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64/plugin:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe/op_tiling/lib/linux/x86_64:/usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/driver::/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib

x,y 变量初始化没问题,npu-smi info 可查看到进程已经分配了显存

root@gds-ascend:/data/projects/LMCache-Ascend# npu-smi info 
+------------------------------------------------------------------------------------------------+
| npu-smi 25.2.2                   Version: 25.2.2                                               |
+---------------------------+---------------+----------------------------------------------------+
| NPU   Name                | Health        | Power(W)    Temp(C)           Hugepages-Usage(page)|
| Chip                      | Bus-Id        | AICore(%)   Memory-Usage(MB)  HBM-Usage(MB)        |
+===========================+===============+====================================================+
| 16    910B4               | OK            | 72.1        42                0    / 0             |
| 0                         | 0000:15:00.0  | 0           0    / 0          2900 / 32768         |
+===========================+===============+====================================================+
+---------------------------+---------------+----------------------------------------------------+
| NPU     Chip              | Process id    | Process name             | Process memory(MB)      |
+===========================+===============+====================================================+
| 16      0                 | 207848        | python                   | 116                     |
+===========================+===============+====================================================+

我要发帖子