-
python test/distributed/_tensor/experimental/test_tp_transform.py TensorParallelTest.test_tp_transform_e2e (With V2 enabled)
**what is going on ?**
we hit this error:
RuntimeError: Attempting t…
-
I'm trying to using torchscript.jit.trace to compile stable-diffusion-v1.4 and convert it into stablehlo.
But the conversion failed because of Upsample op in stable-diffusion.
```
%9885 = stableh…
-
The Llama3 shared codebase demo currently handles prefill input prep, looped prefill, decode input prep, decode trace capture, and decode trace execution.
The Llama3 demo should be refactored to use …
-
Getting an internal assert failure:
```
E1120 16:27:42.446000 166428 site-packages/torch/_subclasses/fake_tensor.py:2301] [0/1_1] failed while attempting to run meta for aten._upsample_bilinear2d_aa…
-
# 🐛 Bug
Fantasization / conditioning model on new data points renders the model unexportable to TorchScript/not traceable with JIT. Models cannot be JIT traced/exported to Torchscript once `get_fan…
-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but …
-
### 🐛 Describe the bug
We use the `torchrun --standalone --nproc-per-node=8 test.py` on a single node. After the `batch_isend_irecv` is completed, we dump the entries and find that the state of `nc…
-
would it be possible to register operations such as na2d using `torch.library.custom_op`,
or otherwise ensure that they participate in operation dispatch?
torch's built in flop counter, FlopCoun…
-
I'm attempting to run inference on a GPU using the layout predictor.
I have made the following changes to the code.
```
class LayoutPredictor:
# ... (previous code) ...
def __init__(sel…
-
Repost from the [PyTorch forum](https://discuss.pytorch.org/t/flex-attention-gaps-in-profiler/211917/1)
I have recently been playing with Flex attention, trying to replace some of my custom triton …