Open nitinmukesh opened 5 days ago
I set up new project today and built diffusers as instructed. Normal inference working fine
Working fine
python inference\cli_demo.py --prompt "A girl riding a bike." --model_path THUDM/CogVideoX1.5-5b --generate_type "t2v"
As mentioned in ReadMe, torchao is installed using
git clone https://github.com/pytorch/ao
cd ao
pip install -e .
The quantized version is still not working
(C:\ai\CogVideo\cv_venv) C:\ai\CogVideo>python inference\cli_demo_quantization.py --prompt "A girl riding a bike." --model_path THUDM/CogVideoX1.5-5b --quantization_scheme fp8 --dtype bfloat16
Traceback (most recent call last):
File "C:\ai\CogVideo\inference\cli_demo_quantization.py", line 26, in <module>
from torchao.float8.inference import ActivationCasting, QuantConfig, quantize_to_float8
ImportError: cannot import name 'ActivationCasting' from 'torchao.float8.inference' (C:\ai\CogVideo\cv_venv\Lib\site-packages\torchao\float8\inference.py)
(C:\ai\CogVideo\cv_venv) C:\ai\CogVideo>pip list
Package Version
----------------------- ------------
absl-py 2.0.0
accelerate 1.1.1
aiofiles 23.2.1
aiohttp 3.9.1
aiosignal 1.3.1
annotated-types 0.6.0
anyascii 0.3.2
anyio 4.6.2.post1
attrs 23.1.0
audioread 3.0.1
Babel 2.14.0
bangla 0.0.2
blinker 1.7.0
blis 0.7.11
bnnumerizer 0.0.2
bnunicodenormalizer 0.1.6
boto3 1.35.63
botocore 1.35.63
braceexpand 0.1.7
cachetools 5.3.2
catalogue 2.0.10
certifi 2023.11.17
cffi 1.16.0
charset-normalizer 3.4.0
click 8.1.7
cloudpathlib 0.16.0
colorama 0.4.6
confection 0.1.4
contourpy 1.2.0
coqpit 0.0.17
cpm-kernels 1.0.11
cycler 0.12.1
cymem 2.0.8
Cython 3.0.7
datasets 3.1.0
dateparser 1.1.8
decorator 4.4.2
deepspeed 0.15.0
diffusers 0.32.0.dev0
dill 0.3.8
distro 1.9.0
docopt 0.6.2
einops 0.8.0
encodec 0.1.1
fastapi 0.115.5
ffmpy 0.4.0
filelock 3.13.1
Flask 3.0.0
fonttools 4.47.0
frozenlist 1.4.1
fsspec 2023.12.2
g2pkk 0.1.2
google-auth 2.25.2
google-auth-oauthlib 1.2.0
gradio 5.6.0
gradio_client 1.4.3
gruut 2.2.3
gruut-ipa 0.13.0
gruut-lang-de 2.0.0
gruut-lang-en 2.0.0
gruut-lang-es 2.0.0
gruut-lang-fr 2.0.2
h11 0.14.0
hangul-romanize 0.1.0
hjson 3.1.0
httpcore 1.0.7
httpx 0.27.2
huggingface-hub 0.26.2
idna 3.6
imageio 2.36.0
imageio-ffmpeg 0.5.1
importlib_metadata 8.5.0
inflect 7.0.0
itsdangerous 2.1.2
jamo 0.4.1
jieba 0.42.1
Jinja2 3.1.2
jiter 0.7.1
jmespath 1.0.1
joblib 1.3.2
jsonlines 1.2.0
kiwisolver 1.4.5
langcodes 3.3.0
llvmlite 0.41.1
Markdown 3.5.1
markdown-it-py 3.0.0
MarkupSafe 2.1.3
matplotlib 3.8.2
mdurl 0.1.2
moviepy 1.0.3
mpmath 1.3.0
msgpack 1.0.7
multidict 6.0.4
multiprocess 0.70.16
murmurhash 1.0.10
networkx 2.8.8
ninja 1.11.1.1
nltk 3.8.1
num2words 0.5.13
numba 0.58.1
numpy 1.26.0
nvidia-ml-py 12.560.30
oauthlib 3.2.2
openai 1.54.4
orjson 3.10.11
packaging 24.2
pandas 1.5.3
pillow 11.0.0
pip 24.2
platformdirs 4.1.0
pooch 1.8.0
preshed 3.0.9
proglog 0.1.10
protobuf 5.28.3
psutil 5.9.7
py-cpuinfo 9.0.0
pyarrow 18.0.0
pyasn1 0.5.1
pyasn1-modules 0.3.0
pycparser 2.21
pydantic 2.9.2
pydantic_core 2.23.4
pydub 0.25.1
Pygments 2.18.0
pynndescent 0.5.11
pyparsing 3.1.1
pypinyin 0.50.0
pysbd 0.3.4
python-crfsuite 0.9.10
python-dateutil 2.8.2
python-multipart 0.0.12
pytz 2023.3.post1
PyYAML 6.0.1
regex 2023.10.3
requests 2.32.3
requests-oauthlib 1.3.1
rich 13.9.4
rsa 4.9
ruff 0.7.4
s3transfer 0.10.3
safehttpx 0.1.1
safetensors 0.4.5
scikit-learn 1.3.2
scikit-video 1.1.11
scipy 1.14.1
semantic-version 2.10.0
sentencepiece 0.2.0
setuptools 75.1.0
shellingham 1.5.4
six 1.16.0
smart-open 6.4.0
sniffio 1.3.1
soundfile 0.12.1
soxr 0.3.7
spacy 3.7.2
spacy-legacy 3.0.12
spacy-loggers 1.0.5
srsly 2.4.8
starlette 0.41.2
SudachiDict-core 20230927
SudachiPy 0.6.8
SwissArmyTransformer 0.4.12
sympy 1.13.1
tensorboard-data-server 0.7.2
tensorboardX 2.6.2.2
thinc 8.2.2
threadpoolctl 3.2.0
tokenizers 0.20.3
tomlkit 0.12.0
torch 2.5.1+cu121
torchao 0.7.0+gitd4ca98f6 C:\ai\CogVideo\ao
torchvision 0.20.1+cu121
tqdm 4.67.0
trainer 0.0.36
transformers 4.46.2
TTS 0.22.0
typer 0.13.0
typing_extensions 4.12.2
tzdata 2023.3
tzlocal 5.2
umap-learn 0.5.5
Unidecode 1.3.7
urllib3 2.2.3
uvicorn 0.32.0
wasabi 1.1.2
weasel 0.3.4
webdataset 0.2.100
websockets 12.0
Werkzeug 3.0.1
wheel 0.44.0
xxhash 3.5.0
yarl 1.9.4
zipp 3.21.0
System Info / 系統信息
torch 2.5.1+cu121 diffusers 0.31.0 torchao 0.7.0+cpu Python 3.11.10 Windows 11
Information / 问题信息
Reproduction / 复现过程
Setup the repo
Merge the following PR https://github.com/THUDM/CogVideo/pull/507
Run inference
Error
Expected behavior / 期待表现
The inference should work