-
Hi!
I am trying to optimize a custom model. Before, I was facing not implemented error. Trying the solution provided [here](https://github.com/NVIDIA-AI-IOT/torch2trt/issues/367). However, now I am f…
-
http://tarql.github.io/#details
> consecutive SPARQL 1.1 CONSTRUCT queries, where PREFIX and BASE apply to any subsequent query
PREFIXes are carried over, but BASE is not (or at least is not resol…
-
### 🐛 Describe the bug
## Description
Before https://github.com/pytorch/pytorch/pull/123732, when running with AOTI, the SDPA pattern can be hit and `torch.ops.aten._scaled_dot_product_flash_atten…
-
Thank you for your outstanding work. I have attempted to apply your methods as described in the paper to RT-4DGS, specifically in the following segment:
`
render_pkg = render(viewpoint_cam, gaussian…
xi-zc updated
2 months ago
-
### 🐛 Describe the bug
Out variants of following ops are causing extra recompilations (in 3rd iteration) in torch.compile when compared to not using out variant,
torch.bmm
torch.topk
torch.chole…
-
### 🚀 The feature, motivation and pitch
Hi,
I want to perform a sparse-dense BMM and compute gradients for the sparse matrix. Is there an operation in torch which does it efficiently? According to…
-
--methy_extract writes output inside bmm folder I give to it instead of writing to current working folder.
For instance if I have:
```
/opt/BitMapperBS/bitmapperBS --methy_extract /data/indexes/ho…
-
### 🐛 Describe the bug
Based on the torch.sparse documentation it sounds like `torch.bmm` supports forward and backward for sparse tensors (but the gradients themselves will be dense). During the b…
-
### 🐛 Describe the bug
version:
python 3.10
torch 2.1.0
cuda 12.1
put breakpoint in row x = x.detach()
```python
import torch
import torchvision
class BoQ_DinoV2(torch.nn.Module):
…
-
```
/opt/conda/lib/python3.8/site-packages/torch/_dynamo/utils.py:1570: UserWarning: Memory Efficient Attention requires the attn_mask to be aligned to, 8 elements. Prior to calling SDPA, pad the las…