Support for float type parameter in inference requests

[wemoveon2]

Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Currently, when we need to pass a float we'd have to pass it as a string or rescale it into an integer and then scale it back into a float in the model files.

Describe the solution you'd like
A clear and concise description of what you want to happen.

Would like for InferParameter to support double_param as a custom parameter
https://github.com/triton-inference-server/common/blob/468eb216b01b375b83590b1e206d1c8cf4160b38/protobuf/grpc_service.proto#L470-L476

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Currently converting to a string and then converting it back before it's used, which isn't ideal.

Additional context
Add any other context or screenshots about the feature request here.

[tanmayv25]

@wemoveon2 Great catch! We will support this!

[wemoveon2]

Hey, any updates? is this feature planned for a release?

[fpetrini15]

Hello @wemoveon2, unfortunately we had to prioritize other urgent items over the last few releases. This feature is not currently planned for a release, but I hope to have an update for you soon! When I do, I'll link you to the corresponding PR.

[fpetrini15]

Hello @wemoveon2, I have merged the PRs relating to this request. Double type parameters will be supported in the 23.02 release!