-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
2.18.0-dev20240925
### Custom code
Yes
### OS platform and distributi…
-
If we use the output of slicing a shape with a negative index in certain operations, we get a failure:
```py
>>> a = tp.Tensor([1, 2, 3])
>>> a.shape
shape([3], dtype=int32, loc=gpu:0, shape=[1])
>>>…
-
### Overview ###
This issue is a tracker for the next steps of enabling the data tiling fusion improvements, which are currently behind the `--iree-dispatch-creation-experimental-data-tiling` flag. O…
-
Hello, I have a question in train a time-dependent energy prediction model. In the file energy_model.py, the loss_energy is about a property in the dataset, i.e. batch.y, for example it represents the…
-
### What happened?
On compiling a model with int8 quantization one of the dispatches fails to compile with the following error:
```
error: One or more operations with large vector sizes (16384 …
-
Hello TT-BUDA Maintainers/Team,
I'm working with the tt-buda project and have a couple of questions regarding its implementation. I reviewed the documentation and relevant modules but couldn't fin…
-
### 🚀 The feature, motivation and pitch
I'm working on an AI for Dr. Mario and would like to look for certain patterns on the game board. This operation is quite naturally represented as a convolutio…
dmwit updated
13 hours ago
-
This is a proposal on how to approach distribution of an MLIR program across multiple homogeneous physical devices that have peered memory. It is intended to improve memory usage under NUMA. Devices/Q…
-
### Suggestion Description
Low-precision tensor operations are rising in usage as techniques such as LLM quantization gain traction in contemporary machine learning ecosystems. As such, it is appropr…
-
When the `Triton::MakeTensorPtrOp` has to be rewritten by the `RewriteTensorPointer` pass to use "regular" memory operations, the generated code seems less performant than a code directly written usin…