-
### Description of the bug:
Hello,
I'm encountering an issue when trying to export a model to tflite with quantization. It appears that the tensor shapes are being altered incorrectly somewher…
-
### 🐛 Describe the bug
First I wanted to say that FlexAttention is amazing new addition that simplifies and accelerates otherwise complicated attention-mask implementation - so thanks a lot for thi…
-
### System Info
```shell
+-----------------------------------------------------------------------------+
| HL-SMI Version: hl-1.17.0-fw-51.1.0 |
| Driver Ver…
-
I am running a GNN network on a mesh. The inputs are of sizes BxNxC where B is the batch-size, N is the number of input nodes and C is the number of channels per node. This input works well with other…
-
### Description
Run
```
import jax
import jax.numpy as jnp
dtype = jnp.bfloat16
batch_dim = 16
x_shape = (batch_dim, 512, 16, 48)
bias_shape = (batch_dim, 16, 512, 512)
mask_shape = (1, 1, …
-
## Description
When I use your demo/Diffusion/demo_txt2img_xl.py for INT8 datatype inference, it reports an error:
Invoked with: %338 : Tensor = onnx::Constant(), scope: transformers.models.clip…
-
The following code leads to an error:
```python
import torch
from torch.nn.attention.flex_attention import flex_attention
B, H, N, D = 100, 12, 128, 64
dtype = torch.bfloat16
device = torch.…
-
I am currently learning about the example "llama2" by following the instructions provided in the [README](https://github.com/pytorch/executorch/blob/main/examples/models/llama2/README.md). I used the …
-
I read the paper, but I'm not quite sure what 'Output Head' means. For example, if I have a 3D molecular graph of my protein pocket, with each node embedded with features from the BLOSUM62 matrix, and…
-
Hi,
Thanks for your wonderful work, I wonder whether this repo is the official code of
“Multivariate Time-series Anomaly Detection via Graph Attention Network“
fffii updated
5 months ago