-
I have created a simple service:
```python
model_runner = bentoml.sklearn.load_runner("mymodel:latest")
svc = bentoml.Service("myservice", runners=[model_runner])
@svc.api(input=NumpyNdarray()…
-
This is something from our original design for Yatai but still missing in the current implementation. We would want to allow users to describe a deployment's detailed spec via a YAML file, which guara…
-
**Describe the bug**
The act of loading a bento service changes the user's working directory.
**To Reproduce**
```
In [1]: import os, bentoml
...:
...: cwd = os.getcwd()
...: bento_…
-
**Describe the bug**
I am trying to deploy model using bentoml. It doesn't give me full access to run terminal commands in conda env to setup using mim. I tried installing using pip.
**Reproductio…
-
**What happened**: I uploaded bentoml api to aks. I got a 429 error while making a request
**What you expected to happen**:
**How to reproduce it (as minimally and precisely as possible)…
-
### Describe the bug.
I successfully installed ersilia I until encountered these errors while running the dummy model.
On `ersilia -v fetch eos3b5e` I got warnings and error: `ERROR: Could not find …
-
**Is your feature request related to a problem? Please describe.**
Sometimes I may write a tentative fix or a tentative feature on my BentoML fork and use that fix in my company, waiting for the fixe…
-
**Describe the bug**
Currently when doing a "bentoml serve" command from the main branch, the webservice startup fails with:
AttributeError: 'bool' object has no attribute 'get'
For a f…
-
**Bug**
Improper error handling in BentoML application. **Invalid request** courses, 400 and 500 error responses that are never send to `/metrics` endpoint.
**To Reproduce**
Below steps where…
-
- Logging format design
- Logging configuration design
- API Server request/response logging
- Runner input/output logging