-
Trying to run this on the CLI on macOS:
```
insanely-fast-whisper --device mps --batch-size 2 --file-name chunk0.mp3
```
```
NotImplementedError: The operator 'aten::isin.Tensor_Tensor_out' is …
-
Hi,
when trying to run the example script on macOS on a macM1 Max, using mps, I get this error:
> NotImplementedError: The operator 'aten::isin.Tensor_Tensor_out' is not currently implemented fo…
-
RuntimeError: The expanded size of the tensor (1024) must match the existing size (1280) at non-singleton dimension 3. Target sizes: [1, 3, 512, 1024]. Tensor sizes: [3, 512, 1280]
![image](https…
-
### Feature Type
- [X] Adding new functionality to pandas
- [ ] Changing existing functionality in pandas
- [ ] Removing existing functionality in pandas
### Problem Description
Reviewing Arrow …
-
I am trying to implement an adaptive avg pool in candle. However, I guess my implementation will require an API to get the raw data/storage (storaged in plain/flatten array format).
Wondering if ther…
-
#### Is your feature request related to a problem? Please describe.
I would appreciate an API for spiked tensor decomposition
#### Describe the solution you'd like
I am not aware of any algorithm…
-
how to gain this root
-
The following stride=2 conv now is creating extra allocations for the dequant and exceeds shared memory limit.
```mlir
func.func @main$async_dispatch_75_conv_2d_nchw_fchw_2x320x64x64x320x3x3_i32() {
…
-
Hi, this issue is mostly revolving around an instance of implementing a model. Is it possible to support this?
I'm trying to define a `LinearBiased` generic model, which can wrap around the current…
-
Although it may be out of scope, it would be nice to have an example of computing 4bit and 8bit tensors, to save memory bandwidth.