-
### What is the bug?
Our pre-trained tas-b model won't accept a doc with a token length exceeding 512
### How can one reproduce the bug?
Simply upload our tas-b model (in ONNX form or torch_scrip…
-
## Description
(A clear and concise description of what the feature is.)
Will this change the current api? How?
Who will benefit from this enhancement?
## References
- list reference an…
-
`setTruncationStrategy` seems to fail with the output of `getTruncationStrategy` due to a case mismatch.
For a tokenizer in use, `getTruncationStrategy` returns `longest_first`, however, `setTruncati…
-
## Description
DJL has profiler support for `MXNet` and `PyTorch` [[REF](https://djl.ai/docs/development/profiler.html)]. I would like to request to extend this profiler support for `ONNX` engine a…
-
Recently，I wanna use _LiveCellSegmentationBoundaryModel_ to analyze my cell images. However, when I click on Plugin>DeepImageJ>DeepImagJ Run, I got a popup warning:
Then, when I try to run on the …
-
I'm running into completion performance problems on my Macbook Pro Max. I usually get completion performance of about 17 tokens per second with a 13B GGUF model. When I run the same completion task us…
-
## Description
(A clear and concise description of what the bug is.)
### Expected Behavior
(what's the expected behavior?)
### Error Message
(Paste the complete error message, including stack…
-
I'm not sure if this is caused by CUDA 12.1 you are using. Can you try CUDA 11.3? or use PyTorch engine?
_Originally posted by @frankfliu in https://github.com/deepjavalibrary/djl/iss…
-
Sorry for stupid question if it is so. I ask, as the information about AVX2 mentioned only in Windows topic. Also I tried to run the app on Linux (Ubuntu based) and I am not sure if it worked at all. …
-
## Description
I use pytorch, have cuda 121 installed on my computer and cannot easily downgrade.
My computer is running archlinux x64.
How could I get djl to use the gpu?
Will this chang…