PaddlePaddle / PaddlePaddle/FastDeploy

npu 编译后无法使用

Open
#2,580 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.7k
Forks
756
Avg merge
19h 28m
Merged PRs (30d)
4

Description

https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/huawei_ascend.md#%E4%B8%80%E5%8D%8E%E4%B8%BA%E6%98%87%E8%85%BE%E7%8E%AF%E5%A2%83%E5%87%86%E5%A4%87
按照教程

Download the latest source code

git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/python
export WITH_ASCEND=ON
export ENABLE_VISION=ON

python setup.py build
python setup.py bdist_wheel
在 华为 arm npu 上编译 无法使用 报错

[INFO] fastdeploy/vision/common/processors/transform.cc(45)::FuseNormalizeCast  Normalize and Cast are fused to Normalize in preprocessing pipeline.
[INFO] fastdeploy/vision/common/processors/transform.cc(93)::FuseNormalizeHWC2CHW       Normalize and HWC2CHW are fused to NormalizeAndPermute  in preprocessing pipeline.
[INFO] fastdeploy/vision/common/processors/transform.cc(159)::FuseNormalizeColorConvert BGR2RGB and NormalizeAndPermute are fused to NormalizeAndPermute with swap_rb=1
[ERROR] Cannot found attribute beta in op: swish

pip list

Package                Version
---------------------- --------------------
absl-py                2.1.0
annotated-types        0.7.0
anyio                  4.7.0
ascendebug             0.1.0
asgiref                3.8.1
astor                  0.8.1
astroid                3.2.2
asttokens              2.4.1
attrs                  23.2.0
audioread              3.0.1
auto-tune              0.1.0
autograd               1.4
Babel                  2.15.0
bce-python-sdk         0.9.17
blinker                1.8.2
certifi                2024.12.14
cffi                   1.16.0
cfgv                   3.4.0
chardet                3.0.4
charset-normalizer     3.4.1
clang-format           13.0.0
click                  8.1.8
cloudpickle            3.0.0
coloredlogs            15.0.1
comm                   0.2.2
concurrent-log-handler 0.9.25
contourpy              1.2.1
coverage               5.5
cryptography           42.0.8
cycler                 0.12.1
Cython                 3.0.10
dataflow               0.0.1
dbus-python            1.2.16
debugpy                1.8.2
decorator              5.1.1
Deprecated             1.2.14
dill                   0.3.8
distlib                0.3.8
distro                 1.4.0
distro-info            0.23+ubuntu1.1
docker-pycreds         0.4.0
exceptiongroup         1.2.2
executing              2.0.1
Farama-Notifications   0.0.4
fastapi                0.115.6
fastdeploy-python      0.0.0
fastdeploy-tools       0.0.5
filelock               3.15.4
Flask                  3.0.3
flask-babel            4.0.0
flatbuffers            24.3.25
fonttools              4.53.0
future                 1.0.0
gitdb                  4.0.11
GitPython              3.1.43
GPUtil                 1.4.0
gymnasium              1.0.0a2
h11                    0.14.0
hccl                   0.1.0
hccl-parser            0.1
httpcore               1.0.5
httptools              0.3.0
httpx                  0.27.0
humanfriendly          10.0
hypothesis             6.104.1
identify               2.5.36
idna                   3.10
iniconfig              2.0.0
ipykernel              6.29.4
ipython                8.26.0
isort                  5.13.2
itsdangerous           2.2.0
jedi                   0.19.1
Jinja2                 3.1.4
joblib                 1.4.2
jupyter_client         8.6.2
jupyter_core           5.7.2
kiwisolver             1.4.5
llm-engine             0.0.1
llvmlite               0.43.0
MarkupSafe             2.1.5
matplotlib             3.9.0
matplotlib-inline      0.1.7
mccabe                 0.7.0
mock                   5.1.0
mpmath                 1.3.0
msadvisor              1.0.0
mypy                   1.10.0
mypy-extensions        1.0.0
nest-asyncio           1.6.0
networkx               3.3
nodeenv                1.9.1
numpy                  2.2.1
op-compile-tool        0.1.0
op-gen                 0.1
op-test-frame          0.1
opc-tool               0.1.0
opencv-contrib-python  4.10.0.84
opencv-python          4.10.0.84
opt-einsum             3.3.0
packaging              24.1
paddle-custom-npu      3.0.0b2
paddle2onnx            1.2.4
paddlepaddle           3.0.0b2
pandas                 2.2.2
parameterized          0.9.0
parso                  0.8.4
pathlib2               2.3.7.post1
pexpect                4.9.0
pillow                 11.0.0
pip                    24.1.1
platformdirs           4.2.2
pluggy                 1.5.0
pooch                  1.8.2
portalocker            3.0.0
pre-commit             2.17.0
prettytable            3.10.0
prompt_toolkit         3.0.47
protobuf               5.27.2
psutil                 6.0.0
ptyprocess             0.7.0
pure-eval              0.2.2
pycparser              2.22
pycrypto               2.6.1
pycryptodome           3.20.0
pydantic               2.10.4
pydantic_core          2.27.2
pygame                 2.5.2
PyGithub               2.3.0
Pygments               2.18.0
PyGObject              3.36.0
PyJWT                  2.8.0
pylint                 3.2.4
PyNaCl                 1.5.0
pyparsing              3.1.2
pytest                 8.2.2
python-apt             2.0.1+ubuntu0.20.4.1
python-dateutil        2.9.0.post0
python-dotenv          1.0.1
python-multipart       0.0.20
pytz                   2024.1
PyYAML                 6.0.2
pyzmq                  26.0.3
qtconsole              5.5.2
QtPy                   2.4.1
rarfile                4.2
requests               2.32.3
requests-unixsocket    0.2.0
schedule-search        0.0.1
scikit-learn           1.5.0
scipy                  1.14.0
sentry-sdk             2.7.1
setproctitle           1.3.3
setuptools             70.1.1
six                    1.14.0
smmap                  5.0.1
sniffio                1.3.1
sortedcontainers       2.4.0
soundfile              0.12.1
ssh-import-id          5.10
stack-data             0.6.3
starlette              0.41.3
sympy                  1.12.1
te                     0.4.0
threadpoolctl          3.5.0
toml                   0.10.2
tomli                  2.0.1
tomlkit                0.12.5
tornado                6.4.1
tqdm                   4.67.1
traitlets              5.14.3
typing_extensions      4.12.2
tzdata                 2024.1
ubelt                  1.3.3
unattended-upgrades    0.1
urllib3                2.3.0
uvicorn                0.16.0
uvloop                 0.21.0
virtualenv             20.26.3
visualdl               2.5.3
wandb                  0.17.3
wcwidth                0.2.13
websockets             14.1
Werkzeug               3.0.3
wheel                  0.45.1
wrapt                  1.16.0
xdoctest               1.1.1
XlsxWriter             3.0.9

使用 registry.baidubce.com/device/paddle-npu:cann80T13-ubuntu20-aarch64-gcc84-py310 这个镜像的docker

npu 信息

| npu-smi 23.0.6                   Version: 23.0.6                                               |
+---------------------------+---------------+----------------------------------------------------+
| NPU   Name                | Health        | Power(W)    Temp(C)           Hugepages-Usage(page)|
| Chip                      | Bus-Id        | AICore(%)   Memory-Usage(MB)  HBM-Usage(MB)        |
+===========================+===============+====================================================+
| 0     910B3               | OK            | 89.5        50                0    / 0             |
| 0                         | 0000:C1:00.0  | 0           0    / 0          5627 / 65536         |

cpu 信息

Architecture:           aarch64
  CPU op-mode(s):       64-bit
  Byte Order:           Little Endian
CPU(s):                 192
  On-line CPU(s) list:  0-191
Vendor ID:              HiSilicon
  BIOS Vendor ID:       HiSilicon
  Model name:           Kunpeng-920
    BIOS Model name:    HUAWEI Kunpeng 920 5250
    Model:              0
    Thread(s) per core: 1
    Core(s) per socket: 48
    Socket(s):          4
    Stepping:           0x1
    BogoMIPS:           200.00
    Flags:              fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma dcpop asimddp asimdfhm ssbs
Caches (sum of all):
  L1d:                  12 MiB (192 instances)
  L1i:                  12 MiB (192 instances)
  L2:                   96 MiB (192 instances)
  L3:                   192 MiB (8 instances)
NUMA:
  NUMA node(s):         8
  NUMA node0 CPU(s):    0-23
  NUMA node1 CPU(s):    24-47
  NUMA node2 CPU(s):    48-71
  NUMA node3 CPU(s):    72-95
  NUMA node4 CPU(s):    96-119
  NUMA node5 CPU(s):    120-143
  NUMA node6 CPU(s):    144-167
  NUMA node7 CPU(s):    168-191
Vulnerabilities:
  Itlb multihit:        Not affected
  L1tf:                 Not affected
  Mds:                  Not affected
  Meltdown:             Not affected
  Mmio stale data:      Not affected
  Retbleed:             Not affected
  Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl
  Spectre v1:           Mitigation; __user pointer sanitization
  Spectre v2:           Not affected
  Srbds:                Not affected
  Tsx async abort:      Not affected

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with docs/cn/build_and_install/huawei_ascend.md and python/setup.py, then reproduce the build and runtime commands in the stated Ascend ARM Docker image. Investigate the reported “Cannot found attribute beta in op: swish” failure in the Ascend execution path; done means the built package runs successfully on the NPU.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, python
Domain
backend, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.