Reputation: 21
Commands I have tried:
python -m streamdiffusion.tools.install-tensorrt
Error generated by the above command:
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com, https://pypi.nvidia.com
Collecting tensorrt-bindings
Downloading tensorrt-bindings-9.2.0.post12.dev5.tar.gz (6.8 kB)
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error
× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [16 lines of output]
Traceback (most recent call last):
File "<string>", line 2, in <module>
File "<pip-setuptools-caller>", line 34, in <module>
File "C:\Users\Owner\AppData\Local\Temp\pip-install-b73tmy1x\tensorrt-bindings_53f09f435d4542748e4e8641602be581\setup.py", line 137, in <module>
raise RuntimeError(open("ERROR.txt", "r").read())
RuntimeError:
###########################################################################################
The package you are trying to install is only a placeholder project on PyPI.org repository.
This package is hosted on NVIDIA Python Package Index.
This package can be installed as:
```
$ pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com tensorrt-bindings
```
###########################################################################################
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed
× Encountered error while generating package metadata.
╰─> See above for output.
note: This is an issue with the package mentioned above, not pip.
hint: See above for details.
I am doing this without the venv virtual environment.
I tried to use TensorRT to generate images faster, but got this error.
There is also a conventional code called pipe.enable_xformers_memory_efficient_attention()
.
Using this, there are no major problems with the code.
However, it will slow down the generation speed.
How to solve this error?
Upvotes: 0
Views: 1071
Reputation: 16758
The error says it all:
The package you are trying to install is only a placeholder project on PyPI.org repository.
This package is hosted on NVIDIA Python Package Index.
This package can be installed as:
```
$ pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com tensorrt-bindings
```
Similarly, as @journpy suggested, please check https://pypi.org/project/tensorrt/ for details on installing TensorRT
module.
You have to first execute:
pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com tensorrt-bindings
OR you can add a source PyPI server (execute the following code just prior to using pip
):
export PIP_EXTRA_INDEX_URL='https://pypi.nvidia.com'
And then restart your installation procedure for the remaining modules (should you have them).
Upvotes: 0