-
**Is your feature request related to a problem? Please describe.**
Many production instances have more than one, or even a handful of, models. Given that the containerized service is quite heavy (300…
-
when i use bentoml to deploy model in docker, i can only deploy one model for one docker . whether i can deploy multiply models in docker for one time ,so models will share same resources. thank you …
-
**Describe the bug**
I use the auto_pip_dependencies on the env_decorator for my Service
@bentoml.env(auto_pip_dependencies=True)
After I save the Service - as expected the BentoML autogenerates …
-
**Describe the bug**
This issue happens only if yatai-service uses the default local disk storage repository.
It doesn't happen if configured to use S3 / Minio for storing Model Artifacts.
The ca…
-
OpenShift version: v3.11
K8 version: v1.11
Tekton Pipeline version: v0.12.1
Issue: Unable to run BentoML pipelines using tekton based CI/CD pipeline. The pipeline deploys the application pod howeve…
-
**Describe the bug**
I started up the YataiService on Docker (RHEL Base Image)
```
bentoml yatai-service-start --debug --verbose
[2020-08-27 07:40:38,709] DEBUG - Enabling gRPC server reflecti…
-
**Is your feature request related to a problem? Please describe.**
Is the new version stable in order to update pypi and use transformers?
I want to deploy a Transformer model from HuggingFace but t…
-
**Describe the bug**
On my RHEL docker container:
If I use plain-flask - the Model API is NOT accessible outside of the container:
`bentoml serve /`
However, if I ssh into the container and try in…
-
**Describe the bug**
I believe this is a bug, but I might just be missing how to properly use the containerize functionality.
The Dockerfile generated by https://github.com/bentoml/BentoML/blob…
-
**Describe the bug**
I executed this Jupyter notebook running locally within Vscode.
https://colab.research.google.com/github/bentoml/gallery/blob/master/onnx/resnet50/resnet50.ipynb
It produc…