nodes/comfyanonymous-ComfyUI_TensorRT
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update requirements.txt (#56)

Browse Source 
Add nvidia pip index to fix missing tensorrt_bindings package.

Installing `tensorrt` no longer pulls in the required `tensorrt_bindings` package.  Adding nvidia's pypi index resolves this issue.

Current:
`python -s -m pip install "tensorrt>=10.0.1" --dry-run --force-reinstall`
```
Collecting tensorrt>=10.0.1
  Using cached tensorrt-10.2.0.post1-py2.py3-none-any.whl
Collecting tensorrt-cu12==10.2.0.post1 (from tensorrt>=10.0.1)
  Using cached tensorrt_cu12-10.2.0.post1-py2.py3-none-any.whl
Would install tensorrt-10.2.0.post1 tensorrt-cu12-10.2.0.post1
```

New:
`python -s -m pip install "tensorrt>=10.0.1" --dry-run --force-reinstall --extra-index-url https://pypi.nvidia.com`
```
Looking in indexes: https://pypi.org/simple, https://pypi.nvidia.com
Collecting tensorrt>=10.0.1
  Using cached https://pypi.nvidia.com/tensorrt/tensorrt-10.2.0.post1.tar.gz (16 kB)
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Preparing metadata (pyproject.toml) ... done
Collecting tensorrt-cu12==10.2.0.post1 (from tensorrt>=10.0.1)
  Using cached https://pypi.nvidia.com/tensorrt-cu12/tensorrt-cu12-10.2.0.post1.tar.gz (18 kB)
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Installing backend dependencies ... done
  Preparing metadata (pyproject.toml) ... done
Collecting tensorrt-cu12-libs==10.2.0.post1 (from tensorrt-cu12==10.2.0.post1->tensorrt>=10.0.1)
  Using cached https://pypi.nvidia.com/tensorrt-cu12-libs/tensorrt_cu12_libs-10.2.0.post1-py2.py3-none-manylinux_2_17_x86_64.whl (2017.5 MB)
Collecting tensorrt-cu12-bindings==10.2.0.post1 (from tensorrt-cu12==10.2.0.post1->tensorrt>=10.0.1)
  Using cached https://pypi.nvidia.com/tensorrt-cu12-bindings/tensorrt_cu12_bindings-10.2.0.post1-cp310-none-manylinux_2_17_x86_64.whl (1.1 MB)
Collecting nvidia-cuda-runtime-cu12 (from tensorrt-cu12-libs==10.2.0.post1->tensorrt-cu12==10.2.0.post1->tensorrt>=10.0.1)
  Using cached https://pypi.nvidia.com/nvidia-cuda-runtime-cu12/nvidia_cuda_runtime_cu12-12.6.37-py3-none-manylinux2014_x86_64.whl (897 kB)
Would install nvidia-cuda-runtime-cu12-12.6.37 tensorrt-10.2.0.post1 tensorrt-cu12-10.2.0.post1 tensorrt-cu12-bindings-10.2.0.post1 tensorrt-cu12-libs-10.2.0.post1
```
This commit is contained in:
maedtb
2024-08-03 11:57:45 -04:00
committed by GitHub
parent 81432b613e
commit ef2d9743c2
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
requirements.txt
+2 -1
View File
@@ -1,2 +1,3 @@
tensorrt>=10.0.1
onnx
onnx
--extra-index-url https://pypi.nvidia.com