huggingface / optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

https://huggingface.co/docs/optimum/main/

huggingface/optimum Issues

OPTIMUM Onnx Exporter for openai/clip-vit-large-patch14 model
Updated 6 days ago2
Export AWQ models to ONNX
Updated 6 days ago1
Adding Support For Phi Models
Updated 6 days ago2
request support for transformers4.42
Closed 6 days ago1
Add feature to export CLIPVisionModel from transformers to onnx
Closed 11 days ago
Qwen2 cannot be supported
Updated 11 days ago
TypeError: _unmask_unattended_patched() missing 1 required positional argument: 'unmasked_value' during ONNX export LLaMa
Updated 11 days ago
how can I get a onnx format int4 model？
Updated 12 days ago
ValueError: Trying to export a florence2 model
Updated 12 days ago
Add ORT support for the StableDiffusionControlNetPipeline.
Updated 13 days ago1
Slow packing times for GPTQ
Updated 17 days ago
Wrong output from ONNX speculative decoding (assistant_model)
Updated 18 days ago1
exporting ORTModelForVision2Seq doesn't work correctly on Pytorch 1.11
Updated 19 days ago4
ONNX support for OneFormer Semantic Segmentation Task
Updated 23 days ago2
Add support for export SigLIP models
Updated 24 days ago8
is_cupy_available() can't find CuPy wheel distributions
Updated 25 days ago
Support for Florence 2 model
Updated a month ago
Quantization by optimum-cli ignores 'use_external_data_format' flag in ORTConfig and fails to quantize models >2GB
Closed a month ago
[Bettertransformer] `Transformers 4.41.0 (torch.SDPA-Bert)` breaks bettertransformers Bert, but works in `Transformers 4.40.2`
Closed a month ago7
Support for phi3-v Vision Model
Updated a month ago1
ONNX export support for 4-bit quantized models
Updated a month ago1
Lift upper version limit of transformers for habana
Closed a month ago4
`merge_decoders` mixes up `decoder_model` and `decoder_model_with_past`
Updated a month ago
Could you provide the official onnx model of Qwen-VL-Chat(-Int4)?
Updated a month ago
Add feature to export CLIPVisionModel from transformers to onnx
Closed a month ago
Custom MT5 model ONNX export not able to run
Updated a month ago
trOCR in onnx format does not read full text
Closed a month ago2
trOCR in onnx format does not read full text
Closed a month ago
TypeError: QDQQuantizer.__init__() got an unexpected keyword argument 'static'
Updated a month ago
onnx optimum ORTOptimizer inference runs slower than setfit.export_onnx runtime.InferenceSession inference
Updated a month ago1
I had a problem mimicking this site: https://community.amd.com/t5/ai/developer-blog-build-a-chatbot-with-ryzen-ai-processors/ba-p/680693
Updated a month ago
Support for `torch.export.export`
Updated 2 months ago2
onnx export for cuda does not work
Updated 2 months ago7
RuntimeError: Expected all tensors to be on the same device, but found at least two devices
Updated 2 months ago2
Trying to export a cohere model, that is a custom or unsupported architecture, but no custom onnx configuration was passed as `custom_onnx_configs`.
Updated 2 months ago
Add support for porting CLIPVisionModelWithProjection
Updated 2 months ago
Phi-3 support for openvino export not working
Updated 2 months ago1
Not able to export a transformer model to onxx (SJ-Ray/Re-Punctuate)
Updated 2 months ago
Unable to generate question-answering model for Llama and there is also no list of what are the supported models for question-answering
Updated 2 months ago
Add LLava ONNX export has a problem
Updated 2 months ago1
Support for Starcoder2 with ORTModelForCausalLM for Faster Inference
Updated 2 months ago
ONNX converted Whisper model takes more than twice the VRAM of the torch version
Updated 2 months ago
`Graph Output Error` when loading optimizing model after running `optimizer.optimize`
Updated 2 months ago
how to change optimum temporary path ?
Updated 2 months ago1
Support for Meta LLaMA 3 with ORTModelForCausalLM for Faster Inference
Updated 2 months ago1
circular dependency issue
Updated 2 months ago1
Improve inference time TrOCR
Updated 2 months ago
ai21labs/Jamba-tiny-random support
Updated 2 months ago
gemma-2b static quantized, generate text makes no sense
Updated 2 months ago
no attribute '_TASKS_TO_AUTOMODELS' error
Updated 2 months ago