InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Unexpected input data type. Actual: (tensor(int32)) , expected: (tensor(int64)
|
|
2
|
3204
|
July 9, 2023
|
Static Quantization with Own dataset
|
|
3
|
390
|
July 1, 2023
|
Is there a way to include the text_projection and/or embedding normalization in an optimum-optimized CLIPTextModelWithProjection?
|
|
8
|
508
|
July 1, 2023
|
Support onnx opset 9 for T5 & GPT_neox
|
|
1
|
282
|
July 1, 2023
|
Are object detection models supported in optimum?
|
|
3
|
259
|
June 22, 2023
|
How to use the cache_dir along with optimum-cli export
|
|
5
|
322
|
June 16, 2023
|
ONNX Flan-T5 Model OOM on GPU
|
|
2
|
1196
|
June 15, 2023
|
Potential Memory Leak for ORTModelForCausalLM with TensorRT Providor
|
|
4
|
529
|
June 2, 2023
|
HOw to make optimum make use of all available GPUs?
|
|
7
|
1561
|
June 1, 2023
|
ONNX vs. Apache TVM
|
|
0
|
326
|
June 1, 2023
|
Huggingface Optimizer
|
|
2
|
315
|
May 25, 2023
|
Optimum Exporter TFLite error
|
|
4
|
556
|
May 18, 2023
|
Custom model export to onnx-runtime
|
|
7
|
799
|
May 9, 2023
|
Optimisation and Quantization of Tensorflow Model
|
|
1
|
352
|
May 3, 2023
|
AttributeError: 'NoneType' object has no attribute 'pad_token'
|
|
1
|
1627
|
May 3, 2023
|
Optimum arm64 quantized models on Apple Silicon (M1)
|
|
1
|
692
|
May 3, 2023
|
Intel Xeon vs AMD EPYC for inference on CPU
|
|
0
|
343
|
March 29, 2023
|
Optimum vs Accelerate
|
|
5
|
585
|
March 2, 2023
|
CUDA OOM when export a large model to ONNX
|
|
3
|
1056
|
February 17, 2023
|
How does the ONNX exporter work for GenerationModel with `past_key_value`?
|
|
9
|
1170
|
February 17, 2023
|
Optimum & T5 for inference
|
|
18
|
4408
|
February 8, 2023
|
AutoModelForCausalLM and Openvino
|
|
5
|
1178
|
February 3, 2023
|
Failed to create CUDAExecutionProvider
|
|
4
|
6512
|
January 31, 2023
|
ONNX on GPU memory footprint
|
|
2
|
825
|
January 30, 2023
|
Longformer Optimum ONNX bug: "ValueError: Model requires 3 inputs. Input Feed contains 2"
|
|
1
|
637
|
December 21, 2022
|
Fail: [ONNXRuntimeError] : 1 : FAIL : Deserialize tensor onnx:
|
|
4
|
2375
|
December 7, 2022
|
Getting ValueError when exporting model to ONNX using optimum
|
|
16
|
3405
|
November 25, 2022
|
Optimize an ONNX Seq2Seq model
|
|
3
|
1301
|
November 17, 2022
|
Use of from_pretrained design pattern
|
|
5
|
521
|
November 3, 2022
|
How to use Pipeline with re-ranker model and ORTForSequenceClassification
|
|
1
|
506
|
November 3, 2022
|