-
When I try to run patch_model_for_compiled_runtime on 8bit + aten, the program reports an error. How can I solve this problem?
![image](https://github.com/user-attachments/assets/f0a85477-f36e-4081-b…
-
### 🐛 Describe the bug
I'm experimenting in exporting various MSS models to Executorch. Following the example export scenario in Executorch Documentation, the export terminates in error: 'Operator …
-
### 🚀 The feature, motivation and pitch
Support ATen operator aten::_convert_weight_to_int4pack.
### Alternatives
_No response_
### Additional context
_No response_
-
`aten::__iand_`
from torch
```cpp
// NB: we always take the scalar type of the Tensor
static const register_formula_for broadcasting_tensor_scalar_ops{
{
"a…
-
### 🐛 Describe the bug
```python
>>> from torchcodec.decoders import SimpleVideoDecoder
>>> decoder = SimpleVideoDecoder("video.mp4")
Traceback (most recent call last):
File "", line 1, in
…
-
### Right Case
When I follow the doc : https://github.com/pytorch/executorch/blob/main/examples/models/llama/README.md#enablement,
I export the Llama3.2-1B-Instruct:int4-spinquant-eo8 model to xnnpa…
-
### Search before asking
- [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and found no similar bug report.
### YOLOv5 Component
_No response_
### Bug
Pytho…
-
### 🐛 Describe the bug
Hi,
I am running the following commands to build the bare-metal libraries, as mentioned in the documentation (https://pytorch.org/executorch/stable/executorch-arm-delegate-t…
-
Increased max_new_tokens to 16384 and received the following crash. Code is updated as of creation of this issue. The prompt was a bit long having an additional 250 lines of source code context.
Un…
-
Hi! when I try to run a python [scripts](https://github.com/pytorch/PiPPy/blob/main/examples/llama/pippy_llama.py) for llm inference in pipeline parallelism on single server with multi GPUs. It turned…