-
### What happened + What you expected to happen
**Issue Summary**
We've identified a potential performance bottleneck within Ray Serve due to the limitation of having a single ProxyActor per node.…
-
It would be nice for testing and development if we could find an alternative to OpenAI that is free at low volumes.
Some ideas that I have not yet dug into:
- [Hugging Face Inference API](https:…
-
### Describe the bug
Creating a bentoml service with this definition:
```python
@bentoml.service(
resources={"cpu":1},
metrics={
"enabled": True,
"duration": {
"buckets…
-
# KServe: A Robust and Extensible Cloud Native Model Server
## Related Issues
* #21
## Article Source
* [KServe: A Robust and Extensible Cloud Native Model Server](https://thenewstack.io/kser…
-
reference: https://github.com/protectai/ai-exploits/blob/main/bentoml/README.md
I think it is easy to exploit but I must find a solution to create a python pickle easily with java.
-
### Describe the bug
'bentoml containerize' doesn't include the model specified in 'bentofile.yaml' in the image. Running the command:
```
docker run -it --rm -p 3000:3000 predictor:lkpxx2u5o24wp…
-
### Describe the bug
I am working on an M3 mac. New mac, didn't adjust the settings.
When I run the command
`openllm repo update`
I have the following issue :
RepresenterError: ('cannot repr…
-
### Describe the bug
I'm having issues defining custom histogram buckets for my service, following the documentation [here](https://docs.bentoml.com/en/latest/guides/configurations.html#metrics). I…
-
### Describe the bug
Hi there,
when creating a new bento service with cuda (any cuda version) in the new version (1.3.1), my bentoml build started to fail on:
`pip not found` when trying to run t…
-
/kind bug
**What steps did you take and what happened:**
If you enable logging, the agent sidecar added breaks streaming responses. Instead of a streamed responses, the caller only gets any re…