model_navigator
model_navigator copied to clipboard
Triton Model Navigator is an inference toolkit designed for optimizing and deploying Deep Learning models with a focus on NVIDIA GPUs.
Hi i am trying to convert the donut model which is built on PyTorch lightning and its throwing me the following error. **2022-09-27 15:02:35,649 INFO Navigator API: PyTorch to ONNX...
When can NAV support creating Triton Repo for this new backend? Is it on your roadmap? https://github.com/triton-inference-server/tensorrtllm_backend
This install: `pip install -U --extra-index-url https://pypi.ngc.nvidia.com triton-model-navigator[]` breaks pips parser. This works instead: `pip install -U --extra-index-url https://pypi.ngc.nvidia.com triton-model-navigator[extras]`
I have 2 separate questions which I could not find an answer yet, so post it here hope someone can answer: 1. When doing TRT conversion from torchscript to trt....
I am trying to follow the tutorial from your repository using the Triton server. However, I am encountering the following errors: # ./optimize.py Traceback (most recent call last): File "./examples/01_optimize_torch_linear_model/./optimize.py",...
get_output_metadat**e**_impl -> get_output_metadat**a**_impl