-
### 🐛 Describe the bug
As of `torch==2.4`, we're unable to register an out-of-tree backend using the `PrivateUse1` mechanism described in [this documentation](https://pytorch.org/tutorials/advanced/e…
-
I used docker image "flexflow/flexflow-cuda-12.1:latest" to run flexflow on a 24GB RTX 3090,but it generated a out of memory error:
```
import flexflow.serve as ff
ff.init(num_gpus=1, memory_per…
-
Hey team, first of wonderful I have a few questions:
1) How is it different from any other OCR model for is it confined only for extraction or anything else.
2) Is there a model available which can …
-
**Description**
bug when deploying Macbert
**Triton Information**
I use the official image: nvcr.io/nvidia/tritonserver:21.09-py3
```
NVIDIA Release 21.09 (build 27443074)
Copyright (c) 20…
-
Hi
this error happend when run detect.py:
File "E:\ANPRir\yolov7_env\lib\site-packages\torchvision\ops\boxes.py", line 40, in nms
return torch.ops.torchvision.nms(boxes, scores, iou_thresh…
-
It has occurred to me, during my toying with [gpuRcuda](https://github.com/gpuRcore/gpuRcuda) that I should be able to find a way to simply allow the user to indicate they wish to use the CUDA backend…
-
We select the backend at build time by selecting CUDA, Vulkan, SYCL, etc. Wouldn't it be better if you build with the backends you want to support and then select the backend at runtime? It's literall…
-
Hey,
when I try to use 3 GPUs but only 2 are available the library behaves as expected and the third process crashes.
```
python gpu-acquisitor.py --backend pytorch --id 1 --nb-gpus 1 & python3 g…
-
### What happened?
When using multiple AMD Radeon RX 7900 XTX (ROCM) graphics cards for different models, an Out of Memory Error occurs when the context size is significantly less than the maximum. T…
-
### 🚀 The feature, motivation and pitch
Currently, [SPDA](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html#torch.nn.functional.scaled_dot_product_atte…