NVIDIA / TensorRT-Model-Optimizer

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.
https://nvidia.github.io/TensorRT-Model-Optimizer
Other
557 stars 40 forks source link

test fail with compiling error AttributeError: _ARRAY_API not found #87

Open braindevices opened 1 month ago

braindevices commented 1 month ago

Can we release the build with numpy2?

+ exec python -c 'import modelopt.torch.quantization.extensions as ext; print(ext.cuda_ext); print(ext.cuda_ext_fp8)'

A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.1.2 as it may crash. To support both 1.x and 2.x                                                                                                                            
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.                                                                                                                 

If you are a user of the module, the easiest solution will be to                                                                                                                    
downgrade to 'numpy<2' or try to upgrade the affected module.
We expect that some modules will need time to support NumPy 2.

AttributeError: _ARRAY_API not found
numpy                    2.1.2
torch                    2.4.1
torch_tensorrt           2.4.0
torchaudio               2.4.1
torchinfo                1.8.0
torchmetrics             1.4.3
torchprofile             0.0.4
torchvision              0.19.1
nvidia-cublas-cu12       12.1.3.1
nvidia-cuda-cupti-cu12   12.1.105
nvidia-cuda-nvrtc-cu12   12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12        9.1.0.70
nvidia-cufft-cu12        11.0.2.54
nvidia-curand-cu12       10.3.2.106
nvidia-cusolver-cu12     11.4.5.107
nvidia-cusparse-cu12     12.1.0.106
nvidia-modelopt          0.17.0
nvidia-nccl-cu12         2.20.5
nvidia-nvjitlink-cu12    12.5.82
nvidia-nvtx-cu12         12.1.105
kevalmorabia97 commented 1 month ago

For now we dont support Numpy 2.0 since it has some backward breaking changes that we have not looked into migrating. Is it possible for you to use numpy 1.x?