-
**Describe the bug**
I've downloaded the repo and ran the quick-start tutorial (Python version, not noteobok), where the only change was to add a yatai_url to the save function (I have a Yatai serv…
-
**Describe the bug**
I'm trying to store a model with a custom loss function. I'm not interested at the loss function at inference time, so it's ok if the model loading totally ignores the loss fun…
-
**Describe the bug**
When using `JsonInput` (or, I believe, any input that uses `@decompress_gzip_request`), inference fails.
**To Reproduce**
Steps to reproduce the issue:
1. Follow steps out…
-
**Describe the bug**
When using a self hosted MinIO as S3 storage, the generated presigned url contains the amazonaws domain, such as
'https://yatai-bucket.s3.amazonaws.com/IrisClassifier/26.tar.gz?…
-
**Describe the bug**
I'm getting this error when trying to serve a bento service with `bentoml serve BentoService:latest --run-with-ngrok`:
.
Have this message when serializing on disk :
```
LGBMClassifier(early_stopping_rounds=5, learning_rate=0.001, n_estimators=10,
…
-
**Is your feature request related to a problem? Please describe.**
When a new version of the model is produced, it is a common practice to compare its performance & behavior against the previous ve…
-
**Describe the bug**
I have Yatai service deployed on Kubernetes. When encountering an issue with an operation (e.g. in this case a missing IAM permission when attempting to deploy a service to Lam…
-
**Describe the bug**
As of BentoML 0.9.0, dependencies in `pip_packages` that have no version constraints (as in `pandas`, not `pandas>=1` or `pandas==1.1.0`) are automatically pinned to the version …