-
Hello,
I have two related problems with torchscript compilation from `torch_neuron` package. It seems that all is static as the `batch_size` and `padding_length` for the tokenizer. Whenever, I want…
-
Hello bentoml team 👋
I am trying to build a Yatai production ready platform on AZURE.
The database is hosted on an external Azure Postgres Single server but I am unable to configure the connectio…
-
**Describe the bug**
When deploying a service with a custom Runnable containing an error, the `bentoml serve` fails to properly start and doesn't show the error in the logs.
**To Reproduce**
…
smidm updated
2 years ago
-
Getting this error when using a custom YOLOv5 model I trained that I loaded and saved using torch hub.
## Error
```
anaconda3/envs/yolov5/lib/python3.7/site-packages/torch/serialization.py │
…
-
### Describe the bug
I am trying to create a service using the quickstart guide and getting issues around sklearn -
```
Error: [cli] `build` failed: sklearn is required in order to use the modul…
-
Currently if users install bentoml from source on windows, there isn't a easy way to setup and configure the environment variable. This means whenever users do `bentoml build`, only the latest changes…
-
I'm running a production server that serves a sklearn (iris_classifier) model first with 1 BentoML worker and then with 2 BentoML workers (the rest of the system configuration stays the same for both …
-
**Is your feature request related to a problem? Please describe.**
Currently `api` endpoints can support locally defined schemas for inputs with [recently](https://github.com/bentoml/BentoML/issues/1…
-
**Is your feature request related to a problem? Please describe.**
Currently, the readiness probe does not bother to check anything; it just returns 200 OK if the app is started up. However, in case …
-
I'm trying to follow the BentoML tutorial [1] to use Bento's API as a custom model deployment on Google Vertex IA (former Google IA Platform). Although the tutorial works, I'm facing some memory issue…