mak

Service fails to run on MacBook with M1 (only CPU inference)

1

I have modified the Dockerfile to be able to build the docker image on M1 (I can also create PR for that). Namely, I added these two steps to build...

Provide additional properties to Snackbar

1

Is it possible to provide additional properties to the Snackbar like: - `anchorOrigin` ex: `anchorOrigin={ vertical: 'bottom', horizontal: 'left' }` - add "X" button to close maually [snackbar API](https://mui.com/material-ui/api/snackbar/)

Docker build fail on MacOS 12 on Apple Silicon (M1)

4

I have cloned the repo and just start `./BuildDockerImage.sh` (does not matter if executing with or without `sudo`). No matter which terminal I use (`zsh` or `fish` in my case)...

bug: Inference fails for `docker run` with `google/flan-t5-large` model with `pytorch` on CPU

1

### Describe the bug The following `docker run` command starts the service, shows the available models but fails to run the completion: ``` docker run --rm -it -p 3000:3000 ghcr.io/bentoml/openllm...

Update optional.md

2

Fix typo in docu: `name: Annoated[str, typer.Argument()]` -> `name: Annotated[str, typer.Argument()]`

Every component return "Component Error"

9

python: python 3.10 OS: Win10 Related pip packages: ``` streamlit-elements 0.1.0 streamlit 1.9.0 ```

Re-use Session object not to create a new connection each time

1

When doing a lot of requests to the same endpoint, it is probably helpful for runtime (and also is "cheaper" on OA server side, I guess) not to create a...

### Proposal It would be great to use non-OpenAI APIs. For example, in the real setting I can use Llama2 or even FlanT5, host it somewhere, expose API endpoint, set...