-
Hello,
I tried to compile with neuron a multilingual roBERTa model using:
```
# Number of Cores in the Pipeline Mode
neuroncore_pipeline_cores = 8
# Compiling for neuroncore-pipeline-cores=…
-
**What steps did you take and what happened:**
- Visit the documentation link at: https://kserve.github.io/website/0.9/modelserving/inference_api/
- Notice that routes explaining `/v2` endpoints suc…
-
Hello,
I'm trying to follow the [tutorial notebook](https://github.com/aws-neuron/aws-neuron-sdk/blob/master/src/examples/pytorch/bert_tutorial/tutorial_pretrained_bert.ipynb) (compiling a HF model…
-
I need to pass several types of metadata for each of my requests. @adriangonz as per our [community slack conversation](https://seldondev.slack.com/archives/C03DQFTFXMX/p1671494800794449) the `types.p…
-
**Describe the bug**
Because torchserve uses torch.profiler since version 0.2.0, the current docker/serve/Dockerfile throws an error.
See https://github.com/pytorch/serve/issues/1548
**Bug …
-
## Context
* torchserve version: torchserve:0.4.1-gpu
* torch-model-archiver version: 0.4.2
* torch version: 1.9.0
* torchvision version [if any]: N/A
* torchtext version [if any]: N/A
* tor…
-
### 🐛 Describe the bug
I installed serve in a new venv by following the process in the readme, i.e.
python ./ts_scripts/install_dependencies.py --cuda=cu117
pip install torchserve torch-model-arc…
-
🐛 Bug report
I'm trying to use a custom crowd counting model and while serving it gives me an error while importing custom model libraries.
Python Import code is like below:
```python3
mo…
-
**Context**: For inference (map creation) a TorchScript model is packaged into a TorchServe docker container which is then deployed into Google Cloud Run to allow parallel predictions for each pixel o…
-
**Context**: A new docker image is released with every package version: https://github.com/nasaharvest/openmapflow/actions/workflows/docker.yaml
**Issue**: From version 0.1.0 to 0.1.1 the docker im…