search

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
574 stars 43 forks source link

Install failed on Centos 7 with Cuda12.2 #103

Closed Valerianding closed 2 weeks ago

Valerianding commented 2 weeks ago

After create a new venv with conda & python==3.8

pip install "nvidia-modelopt[all]~=0.19.0" --extra-index-url https://pypi.nvidia.com
ERROR: Ignored the following versions that require a different python version: 1.1.0 Requires-Python >=3.9.0
ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu~=1.18.0; (platform_machine != "aarch64" and platform_system != "Darwin") and extra == "all" (from nvidia-modelopt[all]) (from versions: 1.2.0, 1.4.0, 1.6.0, 1.8.0, 1.9.0, 1.10.0, 1.11.0, 1.11.1, 1.12.0, 1.12.1, 1.13.1, 1.14.0, 1.14.1, 1.15.0, 1.15.1, 1.16.0, 1.16.1, 1.16.2, 1.16.3)
ERROR: No matching distribution found for onnxruntime-gpu~=1.18.0; (platform_machine != "aarch64" and platform_system != "Darwin") and extra == "all"

ENV: os: centos7 cuda: 12.2 driver: 535.54.03 python: 3.8

kevalmorabia97 commented 2 weeks ago

Seems like an issue with ONNX Runtime: https://github.com/microsoft/onnxruntime that they stopped supporting CentOS 7 after 1.16.3 Also note that CentOS 7 is already at end of life (since Jun 30, 2024) and soon ModelOpt will stop supporting CentOS 7. Similarly PyTorch no longer supports Python 3.8 so ModelOpt will also stop support Python3.8 in the near future