-
### Your current environment
```text
WARNING 11-14 02:19:07 _custom_ops.py:20] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'")
Collecting environment information…
-
### 🐛 Describe the bug
In the four variants of `nn.init.zeros_` at the bottom: the expected behavior is to see some zeros in the printed matrix. Howver, when slicing a partial matrix `[:2]`, none o…
-
### Your current environment
The output of `python collect_env.py`
```text
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A…
-
## Describe the bug
When using the `PyramidDiTForVideoGeneration` pipeline, a `ValueError` occurs due to the covariance matrix not being positive definite when sampling from a multivariate normal dis…
-
### Your current environment
The output of `python collect_env.py`
```text
Collecting environment information...
PyTorch version: 2.3.1+cpu
Is debug build: False
CUDA used to build PyTorch: …
-
### 🐛 Describe the bug
Invoking a compiled model under FlopCounterMode context results in a slower compiled model.
If we run our benchmark _before_ the model is instrumented with FlopCounterMode, …
-
### 🐛 Describe the bug
# Bug Description
Similar to [42246](https://github.com/pytorch/pytorch/issues/42246), which has been fixed, I encountered the similar error while running `torch.ops.aten.divi…
-
### 🐛 Describe the bug
cannot using:
```
python -m examples.models.llama.export_llama --checkpoint "checkpoint.pth" --params "original_params.json" -kv --use_sdpa_with_kv_cache -X -d …
-
### 🐛 Describe the bug
Not a bug, just a UserWarning which is ignorable. I'm merely doing as instructed in the warning, that is reporting it as an issue here. Searching past issues didn't find th…
-
### 🐛 Describe the bug
according to this link: https://github.com/pytorch/executorch/blob/main/examples/demo-apps/android/LlamaDemo/docs/delegates/qualcomm_README.md
model convert: python3 -m exam…