optimum

optimum copied to clipboard

The safety checker is not working with OVStableDiffusionPipeline. ### System Info ```shell - `diffusers` version: 0.23.0 - Platform: Windows-10-10.0.22631-SP0 - Python version: 3.11.0 - PyTorch version (GPU?): 2.0.1+cpu (False) -...

rupeshs

Make ORTModel PyTorch free

6

### Feature request Currently, ORTModel has a hard dependency on `torch` and `transformers`. Could we make it such that this dependency is soft, and that Optimum + ORTModel can be...

fxmarty

cannot import name 'ORTModelForSeq2SeqLM' from 'optimum.onnxruntime'

4

### System Info ```shell optimum 1.9.1 onnx 1.14.0 onnxconverter-common 1.13.0 onnxruntime 1.15.1 onnxruntime-tools 1.7.0 tf2onnx 1.14.0 transformers 4.31.0 torch 2.0.1 torchaudio 2.0.2 torchvision 0.15.2 ``` ### Who can help? Hi,...

aresa7796

Support BLIP ONNX export & runtime

5

### Feature request I want to export my model to onnx，but an error was happend, like, xxx is not support. such as, if I want export a blip model "Salesforce/blip-image-captioning-large"...

Arrkwen

Assistance exporting git-large to ONNX

2

Hello! I am looking to export an image captioning Hugging Face model to ONNX (specifically I was playing with the [git-large](https://huggingface.co/microsoft/git-large) model but if anyone knows of one that might...

gracemcgrath

open_clip model onnx export not supported

10

### System Info ```shell Python 3.9.16 optimum 1.13.2 Ubuntu 20.04.6 LTS ``` ### Who can help? @michaelbenayoun ### Information - [X] The official example scripts - [ ] My own...

alachyan-ml

### System Info ```shell - optimum : 1.14.1 - huggingface_hub version: 0.19.4 - Platform: Linux-3.10.0-1160.88.1.el7.x86_64-x86_64-with-glibc2.17 - Python version: 3.9.17 - Running in iPython ?: No - Running in notebook ?:...

rangehow

[WIP] Add onnx export support for CLIPSeg models

1

# What does this PR do? Two things need to be updated in transformers: 1. Fix casting [here](https://github.com/huggingface/transformers/blob/fa21ead73db473d88f8eca1ec244aba776fd9047/src/transformers/models/clipseg/modeling_clipseg.py#L1290), [here](https://github.com/huggingface/transformers/blob/fa21ead73db473d88f8eca1ec244aba776fd9047/src/transformers/models/clipseg/modeling_clipseg.py#L199), and [here](https://github.com/huggingface/transformers/blob/fa21ead73db473d88f8eca1ec244aba776fd9047/src/transformers/models/clipseg/modeling_clipseg.py#L175) 2. Add the following line [here](https://github.com/huggingface/transformers/blob/fa21ead73db473d88f8eca1ec244aba776fd9047/src/transformers/models/auto/modeling_auto.py#L549): ```py ("clipseg", "CLIPSegForImageSegmentation"),...

xenova

Community contribution - `BetterTransformer` integration for more models!

25

## `BetterTransformer` integration for more models! `BetterTransformer` API provides faster inference on CPU & GPU through a simple interface! Models can benefit from very interesting speedups using a one liner...

younesbelkada

longT5 BetterTransformer implementation

5

### Feature request longT5 BetterTransformer implementation ### Motivation Encoder-decoder model trained on large context allow machine translation tasks ### Your contribution I looked at the implementation of regular T5 and...

omri-sap