-
I’m encountering issues when trying to convert my YOLOv8x model from torchscript to torch_neuron on Kaggle. Here are the details:
1. YOLOv8x Model (Single Class):
- Trained model file: '.pt'
…
-
Hi,
I tried to trace [LightGlue](https://github.com/cvg/LightGlue) model with inf2 instance but it got error and crash.
Trace command
`model_neuron = torch_neuronx.trace(model, input_features, comp…
-
### Motivation.
`vLLM` has already been adapted to many hardware devices, such as `GPU`, `TPU`, and `XPU`. However, adapting these backends requires implementing separate `Worker/Executor/Model Run…
-
### 🚀 The feature, motivation and pitch
We know that language models exhibit activation sparsity during inference, meaning that they can perform lossless inference even when only a portion of the act…
-
Hi Everyone,
I am testing both PyTorch and Torchsharp with a very basic example (fitting of a single variable non-linear function). When I use Rprop in Pytorch I get a very good fitting, as expected.…
-
-
Hangs on the message "Loading Neuron information" when trying to configure my keyboard.
**To Reproduce**
0. Turn on keyboard and ensure it's connected and working via bluetooth.
1. Launch Bazec…
-
Neurons without incoming synapses that are on a path from an input neuron are not properly handled in the generated network SystemVerilog file. This causes signals to go to an undetermined state (symb…
-
The refractory time after a spike at time $t^*$ is defined for `iaf_psc_delta` and many other neurons via
$$V_m(t) = V_{\text{reset}} \quad \text{for} \quad t^* \leq t < t^* + t_{\text{refract}}$$
…
-
I have an environment that supports both torch-neuronx and torch-xla. When I do simple utility calls I can confirm that the XLA device is being detected and is accurately identified as Neuron. However…