[910B4]Embedding模型返回问题

[JasonFlyBeauty]

System Info / 系統信息

驱动版本：Ascend-hdk-910b-npu-driver_23.0.3_linux-aarch64.run

CANN版本：Ascend-cann-toolkit_8.0.RC3.alpha001_linux-aarch64.run

(xinference) [root@ app]# pip list
Package Version

---

accelerate 1.0.1
aiofiles 23.2.1
aioprometheus 23.12.0
annotated-types 0.7.0
anyio 4.6.2.post1
ascendebug 0.1.0
async-timeout 4.0.3
attrs 24.2.0
auto-tune 0.1.0
bcrypt 4.2.0
certifi 2024.8.30
cffi 1.17.1
charset-normalizer 3.4.0
click 8.1.7
cloudpickle 3.1.0
cryptography 43.0.3
dataflow 0.0.1
decorator 5.1.1
distro 1.9.0
ecdsa 0.19.0
exceptiongroup 1.2.2
fastapi 0.115.4
ffmpy 0.4.0
filelock 3.16.1
fsspec 2024.10.0
gradio 5.4.0
gradio_client 1.4.2
h11 0.14.0
hccl 0.1.0
hccl-parser 0.1
httpcore 1.0.6
httpx 0.27.2
huggingface-hub 0.26.1
idna 3.10
Jinja2 3.1.4
jiter 0.6.1
joblib 1.4.2
llm-datadist 0.0.1
markdown-it-py 3.0.0
MarkupSafe 2.1.5
mdurl 0.1.2
ml_dtypes 0.5.0
modelscope 1.19.2
mpmath 1.3.0
msadvisor 1.0.0
networkx 3.4.2
numpy 1.26.4
nvidia-ml-py 12.560.30
op-compile-tool 0.1.0
op-gen 0.1
op-test-frame 0.1
opc-tool 0.1.0
openai 1.52.2
orjson 3.10.10
packaging 24.1
pandas 2.2.3
passlib 1.7.4
peft 0.13.2
pillow 11.0.0
pip 24.2
psutil 6.1.0
pyasn1 0.6.1
pycparser 2.22
pydantic 2.9.2
pydantic_core 2.23.4
pydub 0.25.1
Pygments 2.18.0
python-dateutil 2.9.0.post0
python-jose 3.3.0
python-multipart 0.0.12
pytz 2024.2
PyYAML 6.0.2
quantile-python 1.1
regex 2024.9.11
requests 2.32.3
rich 13.9.3
rsa 4.9
ruff 0.7.1
safehttpx 0.1.1
safetensors 0.4.5
schedule-search 0.0.1
scikit-learn 1.5.2
scipy 1.14.1
semantic-version 2.10.0
sentence-transformers 3.2.1
setuptools 75.1.0
shellingham 1.5.4
six 1.16.0
sniffio 1.3.1
sse-starlette 2.1.3
starlette 0.41.2
sympy 1.13.3
tabulate 0.9.0
tblib 3.0.0
te 0.4.0
threadpoolctl 3.5.0
timm 1.0.11
tokenizers 0.20.1
tomlkit 0.12.0
torch 2.1.0
torch-npu 2.1.0.post3
torchvision 0.16.0
tornado 6.4.1
tqdm 4.66.5
transformers 4.46.0
typer 0.12.5
typing_extensions 4.12.2
tzdata 2024.2
urllib3 2.2.3
uvicorn 0.32.0
uvloop 0.21.0
websockets 12.0
wheel 0.44.0
xinference 0.16.1
xoscar 0.3.3

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• docker / docker
• pip install / 通过 pip install 安装
• installation from source / 从源码安装

Version info / 版本信息

printenv
SHELL=/bin/bash
HISTCONTROL=ignoredups
CONDA_EXE=/root/miniconda3/bin/conda
_CE_M=
HISTSIZE=1000
HOSTNAME=135-17
PWD=/home/app
LOGNAME=root
CONDA_PREFIX=/root/miniconda3/envs/xinference
MOTD_SHOWN=pam
HOME=/root
LANG=zh_CN.UTF-8
CONDA_PROMPT_MODIFIER=(xinference)
SSH_CONNECTION=192.168.0.16 1249 192.168.135.17 22
TOOLCHAIN_HOME=/usr/local/Ascend/ascend-toolkit/latest/toolkit
ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
SELINUX_ROLE_REQUESTED=
PYTHONPATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe:
TERM=xterm
_CE_CONDA=
USER=root
CONDA_SHLVL=2
SELINUX_USE_CURRENT_RANGE=
SHLVL=1
ASCEND_OPP_PATH=/usr/local/Ascend/ascend-toolkit/latest/opp
CONDA_PYTHON_EXE=/root/miniconda3/bin/python
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/aarch64:/usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/driver:
ASCEND_AICPU_PATH=/usr/local/Ascend/ascend-toolkit/latest
SSH_CLIENT=192.168.0.16 1249 22
CONDA_DEFAULT_ENV=xinference
PATH=/usr/local/Ascend/ascend-toolkit/latest/bin:/usr/local/Ascend/ascend-toolkit/latest/compiler/ccec_compiler/bin:/usr/local/Ascend/ascend-toolkit/latest/tools/ccec_compiler/bin:/root/miniconda3/envs/xinference/bin:/root/miniconda3/condabin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/root/bin
SELINUX_LEVEL_REQUESTED=
ASCEND_HOME_PATH=/usr/local/Ascend/ascend-toolkit/latest
MAIL=/var/spool/mail/root
SSH_TTY=/dev/pts/3
CONDA_PREFIX_1=/root/miniconda3
OLDPWD=/root
_=/usr/bin/printenv

The command used to start Xinference / 用以启动 xinference 的命令

conda create -n xinference python=3.10

conda activate xinference

pip3 install torch==2.1.0 torchvision==0.16.0 --index-url https://download.pytorch.org/whl/cpu -i https://pypi.tuna.tsinghua.edu.cn/simple

pip3 install pyyaml -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install setuptools -i https://pypi.tuna.tsinghua.edu.cn/simple

pip3 install sentence-transformers -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install attrs -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install ml-dtypes tornado -i https://pypi.tuna.tsinghua.edu.cn/simple

pip3 install 'numpy<2.0' -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install decorator -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install torch-npu==2.1.0.post3 -i https://pypi.tuna.tsinghua.edu.cn/simple

pip3 install xinference -i https://pypi.tuna.tsinghua.edu.cn/simple

xinference-local --host 0.0.0.0 --port 9997

xinference launch --model-name bge-m3 --model-type embedding --gpu-idx 0 --host 0.0.0.0

Reproduction / 复现过程

curl -X 'POST' \

'http://0.0.0.0:9997/v1/embeddings'
-H 'accept: application/json'
-H 'Content-Type: application/json'
-d '{
"model": "bge-m3",
"input": "What is the capital of China?"
}'
{"object":"list","model":"bge-m3-1-0","data":[{"index":0,"object":"embedding","embedding":[0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]}],"usage":{"prompt_tokens":0,"total_tokens":0}}

Expected behavior / 期待表现

Embedding模型正常回复

[qinxuye]

哪个模型？

[JasonFlyBeauty]

哪个模型？

我们更换了cann Kernels 问题已解决