-
This is related to the review of `FunFact` for JOSS (see https://github.com/openjournals/joss-reviews/issues/4502)
I understand that your package can do (or approximate) arbitrary tensor decomposit…
-
Currently, `root_decomposition` fails for LazyTensors with a single element with an obscure index error (except for DiagLazyTensor, where it is special-cased). More generally, the iterative low-rank a…
-
Hello
first of all thank you for your great work
i would like to extract the cross attention maps to visualize spatial attention in a synchronized way to my images (during training on my val and a…
-
The straight forward TT-decomposition of a full tensor does not work properly for me.
Minimal example:
```
import tntorch as tn
import torch
import numpy as np
X, Y, Z = np.meshgrid(range(12…
-
### 🐛 Describe the bug
Repro:
```
import torch
import torch._dynamo
@torch.compile(backend="eager", fullgraph=True)
def fn(x):
return torch.functional.split(x, 0)
fn(torch.empty((0,)…
-
Some significant models are blocked by `tfl.lstm` which can be decomposed into already support tflite operations.
Adding the decomposition should unblock these models.
```
/tmp/test.tflite:0:0: n…
-
# 🚀 1. The feature
This RFC proposes using Triton language to implement Intel GPU (`torch.xpu`) kernels.
## 1.1. Motivation
This RFC aims to discuss the XPU kernel implementation with the Trit…
-
Hi. I test the CP decomposition and I met a mistake returned by parafac:
`last, first, vertical, horizontal = parafac(W, rank=rank, init='random')
ValueError: not enough values to unpack (expected 4…
-
#### Issue description
The following code does not work (NB: the `-1` factor in `ops`).
```python
ops = [-1 * qml.Z(0) @ qml.Z(1)]
coeffs = [1.]
reg = qml.registers({"physical": 2, "prep": …
-
Currently using the heatmap approach we can see some basic success from the tensor decomposition (word documents are classified with word docs, malware is classified with malware), however we can do b…