-
### 🚀 The feature, motivation and pitch
For now ,when `ord == inf` ,it fallback to cpu, we should have the implementation when `ord == inf` to same as cuda.
### Alternatives
_No response_
…
-
-
### 🚀 The feature, motivation and pitch
I'd like to export my Bilinear model to onnx, but torch.onnx.dynamo_export does not support for aten._trilinear.
### Alternatives
Torch.onnx.export does not …
-
### 🐛 Describe the bug
I found that `torch.nn.InstanceNorm2d` layer, which by default does not track running mean and var, is failing at runtime. It successfully goes through the lowering process wit…
-
## Description
trt10.5 pytorch-quantization has compile bug.
https://github.com/NVIDIA/TensorRT/blob/release/10.5/tools/pytorch-quantization/src/tensor_quant_gpu.cu#L28-L37
define two macro `AT_DI…
-
Hi, I'm trying to quantize and compile a PyTorch model with some Aten operations not supported by Vitis-AI yet. Specifically, I'm deploying the model (quantizing the model with test mode) but some err…
-
Hello,
I am struggling to trace BLIP2 model from transformers library using `torch_neuronx` to make it work on an inf2. The model I want to trace is the [XXL version](https://huggingface.co/Salesfo…
-
Result: Killed,
No file created.
Logs:
cd /project && python simple_example.py
ckpt path or config path does not exist! Downloading the model from the Hugging Face Hub...
enc_c.ckpt: 100%|██████…
-
Hi! Can you provide codes to reproduce MACs in Table 6(b) in your paper?
I calculate MACs on multiHMR_896_L using fvcore (https://github.com/facebookresearch/fvcore), but I get different outputs from…
-