According to the API:
```rust
inp = inp.to_device(&Device::Cuda(0)?)?;
```
cannot work as `Cuda(...)` expects a type `Device` not an integer.
I'd recommend to instead use `new_cuda(...)`
* first q2 implementation
* First Q4K and Q5K implementations
* fix `q2k` and `q5k`
* Some first cleanups
* run `clippy` on tests
* finally implement `q3k`
* deactivate `q3k` test on macos
* also disable the test on linux
* Fix floating bits in `q3k` dequantization
* Refactoring pass + reorder quants in file
* `fmt`
* Re-add `src` asserts and redefine `dst`
* Sketch the yolo wasm example.
* Web ui.
* Get the web ui to work.
* UI tweaks.
* More UI tweaks.
* Use the natural width/height.
* Add a link to the hf space in the readme.
* Sketching yolo-v8.
* Get the model to load.
* yolo-v8 forward pass.
* Complete(?) the forward pass.
* Fix some shape issues.
* Add the missing padding.
* Process the predictions.
* Some fixes for yolo-v3.
* Use the running stats for inference in the batch-norm layer.
* Get some proper predictions for yolo.
* Avoid the quadratic insertion.
* Add a couple functions required for yolo.
* Add the yolo-v3 example.
* Add minimum and maximum.
* Use the newly introduced maximum.
* Cuda support for min/max + add some testing.
* Allow for more tests to work with accelerate.
* Fix a typo.
* Skeleton files for neon support of quantization.
* SIMD version for q4 vecdot.
* Also simdify the q6k multiplication.
* Add some timings to stable-diffusion.
* Separate the prompt stats from the post-prompt ones in the quantized example.
* Slightly nicer output printing.
* Line up with the llama.cpp implementation.
* Pickle work-in-progress.
* More unpickling.
* More pickling.
* Proper handling of setitems.
* Clippy.
* Again more pickling.
* Restore the example.
* Add enough pickle support to get the list of tensors.
* Read the data from zip files.
* Retrieve the tensor shape.
* Extract the size and dtype.
* More storage types.
* Improve the destructuring.
* Also support ggml files.
* Pickle work-in-progress.
* More unpickling.
* More pickling.
* Proper handling of setitems.
* Clippy.
* Again more pickling.
* Restore the example.
* Add enough pickle support to get the list of tensors.
* Read the data from zip files.
* Retrieve the tensor shape.
* Extract the size and dtype.
* More storage types.
* Improve the destructuring.
