Is it possible to make the first batch as fast as the subsequent ones?
|
|
1
|
86
|
June 25, 2024
|
Are object detection models supported in optimum?
|
|
7
|
839
|
June 21, 2024
|
UnboundLocalError: cannot access local variable 'all_files' where it is not associated with a value
|
|
4
|
1532
|
June 13, 2024
|
Not able run all nodes on DML with optimum
|
|
4
|
384
|
June 6, 2024
|
Not able to run on DML with pipeline
|
|
2
|
339
|
June 6, 2024
|
How to quantize and run inference for CLIP using optimum
|
|
1
|
241
|
June 3, 2024
|
Device_map not wokring for ORTModelForSeq2SeqLM - Potential bug?
|
|
1
|
455
|
May 22, 2024
|
AttributeError: OV_ModelForTokenClassificatio' object has no attribute 'modules'
|
|
1
|
303
|
May 21, 2024
|
ONNX only faster at lower sequence lengths
|
|
2
|
324
|
May 21, 2024
|
Quantization GPTQ
|
|
1
|
231
|
May 21, 2024
|
Trocr after onnx quantisation conversion using optimum-cli , im getting this error
|
|
1
|
361
|
May 20, 2024
|
Optimum onnx-gpu not working inside a docker container
|
|
2
|
1462
|
May 20, 2024
|
Error exporting T5 model to ONNX with optimum-cli
|
|
3
|
802
|
May 7, 2024
|
Export pretrained MT5 model to ONNX
|
|
5
|
621
|
May 3, 2024
|
Regarding input_ids and labels while grouping texts
|
|
3
|
348
|
April 24, 2024
|
FLOPS computation
|
|
1
|
162
|
April 16, 2024
|
Wandb integration run_clm.py
|
|
3
|
218
|
April 17, 2024
|
Regarding max steps, streaming in language modeling
|
|
3
|
234
|
April 13, 2024
|
"Protobuf parsing failed" when onnxruntime opens a quantized model
|
|
0
|
2293
|
March 25, 2024
|
What is the execution provider of optimum[onnxruntime]?
|
|
0
|
291
|
March 11, 2024
|
When exporting seq2seq models with ONNX, why do we need both decoder_with_past_model.onnx and decoder_model.onnx?
|
|
12
|
4570
|
March 7, 2024
|
Darshan Hiranandani - How do I handle rate limits or throttling imposed by an API?
|
|
0
|
330
|
March 5, 2024
|
Trying to use Transformers.js
|
|
0
|
689
|
March 1, 2024
|
Should pruning shrink model?; adjusting sparsity didn't change inference time
|
|
2
|
774
|
February 29, 2024
|
Cannot export to ONNX with optimum.onnxruntime
|
|
0
|
910
|
February 28, 2024
|
Optimize AND quantize with Optimum
|
|
11
|
3287
|
February 10, 2024
|
Improving Quantization Accuracy for ONNX Models with Optimum
|
|
0
|
724
|
February 8, 2024
|
Audio classifier in TFLite format
|
|
0
|
596
|
January 25, 2024
|
Need advice for implementing Greedy Search for ORTModelForSeq2SeqLM
|
|
2
|
595
|
January 17, 2024
|
Optimum roberta base quantization model recall drop 10%
|
|
5
|
470
|
January 15, 2024
|