Ekaterina Aidova
Ekaterina Aidova
@wgzintel @peterchen-intel do you have plan to fix sample code (with clone/without clone)? Looks like initial issue still reproducible
> Looks great, thanks a lot @eaidova @echarlaix thanks, we still investigating impact on models accuracy and quantization on our side. Could you please do not merge these changes, until...
@IlyasMoutawwakil could you please merge?
@SearchSavior stateful is default and recommended scenario for LLMs running, it is expected that stateless models are less performant as there are additional optimizations from openvino side for stateful scenario:...
https://github.com/huggingface/optimum-intel/pull/876
@brmarkus dev model was never uploaed to huggingface hub under openvino account, it has license agreement limitations for that unfortunately, we have only schnell https://huggingface.co/OpenVINO/FLUX.1-schnell-int4-ov
@circuluspibo could you please provide more details about error and which modifications do you perform?
> The documentation in the article has the following issues. @AdamMiltonBarker could you please provide link on article which you follow?
@rathoreaniket007 you comparing static shape exported onnx model with dynamic shapes converted openvino,it does not looks like honest comparison,
Hello @avinashbhat09 this is known issue of pytorch ((do you use torch 2.4, correct?), You can find suggested solutions for that on pytorch forum: https://discuss.pytorch.org/t/failed-to-import-pytorch-fbgemm-dll-or-one-of-its-dependencies-is-missing/201969 issue should be already fixed...