-
Hi,
when I am trying to save the service I keep getting this error.
[2020-12-16 11:29:30,965] WARNING - pip package requirement pandas already exist
[2020-12-16 11:29:30,968] WARNING - pip pac…
-
**Describe the bug**
When i run `bentoml list` from the command line, `BentoML` will blow up stating i am missing a `client` Key. This is incorrect as the documentation states `Optional` for a cl…
-
**Describe the bug**
I'm running Bentoml v0.12.1 and it seems that I still need to use --enable-microbatch in order for microbatching to take effect. Otherwise, `bentoml serve-gunicorn` doesn't b…
-
**Describe the bug**
I have BentoML v0.9.2 running on my infrastructure.
Today, I decided to upgrade to 0.10.1
1. I first upgraded the yatai-service and then my training pipeline.
2. Things were…
-
**Describe the bug**
So we have some services that we are trying to use with Dagster. The issue is that as data flows through the DAG, the service will be hit multiple times in parallel. What we see …
-
**Describe the bug**
During initial testing of `BentoML` using the `Yatai` service over `gRPCs` we encountered a few failed deployments due to permissions relating to `IAM` (want to figure out wh…
-
**Describe the bug**
Attempting to deploy to SageMaker or Lambda fails with this error:
```
Error: sagemaker deploy failed: INTERNAL: has type Provide, but expected one of: bytes, unicode
```
…
-
**Describe the bug**
I want to use `KerasModelArtifact` such that the name of the model is saved and restored. I also want to use `store_as_json_and_weights=True` to forget about the loss function …
-
**Describe the bug**
I found a bug that labels are not saved in YataiService after pushing my bento service.
**To Reproduce**
- [click here to see the example below](https://docs.bentoml.org/…
-
Firstly, thanks everyone who make contribution to bentoML. when i delopy ML model to production situation,I need to use hadoop file system exchange raw data on local prod env.but BentoML only support …