-
Notifications
You must be signed in to change notification settings - Fork 68
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Convert huggingface model to onnx #1888
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it is worthwhile for us to build a package for this onnx model conversion and standardize the UX
8fcc71a
to
488ec9b
Compare
Done |
5f3c9fb
to
e5ff0fc
Compare
e6a05af
to
d80ba02
Compare
serving/docker/lmi.Dockerfile
Outdated
@@ -92,7 +93,9 @@ RUN pip3 install torch==${torch_version} torchvision==${torch_vision_version} -- | |||
transformers==${transformers_version} hf-transfer zstandard datasets==${datasets_version} \ | |||
mpi4py sentencepiece tiktoken blobfile einops accelerate==${accelerate_version} bitsandbytes==${bitsandbytes_version} \ | |||
optimum==${optimum_version} auto-gptq==${auto_gptq_version} pandas pyarrow jinja2 \ | |||
opencv-contrib-python-headless safetensors scipy && \ | |||
opencv-contrib-python-headless safetensors scipy \ | |||
onnxruntime-gpu==${onnx_version} --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/ \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why we need onnxruntime-gpu?, we only use it for conversion
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is needed for O4 optimization. Otherwise this will fail.
Description
Brief description of what this PR is about