Release 0.3.0

Add transcription interface for raw numpy arrays (#491)

## Checks

- [ ] `make lint`: I've run `make lint` to lint the changes in this PR.
- [ ] `make test`: I've made sure the tests (`make test-cpu` or `make
test`) are passing.
- Additional tests:
   - [ ] Benchmark tests (when contributing new models)
   - [ ] GPU/HW tests

[hotfix] Fix scaling for deployments in `ModelHandle` (#528)

## Related issues

<!-- For example: "Closes #1234" -->

## Checks

- [x] `make lint`: I've run `make lint` to lint the changes in this PR.
- [x] `make test`: I've made sure the tests (`make test-cpu` or `make
test`) are passing.
- Additional tests:
   - [ ] Benchmark tests (when contributing new models)
   - [x] GPU/HW tests

Update CI to build/push `cu121` images on release (#513)

<!-- Thank you for your contribution! Please review
https://github.com/autonomi-ai/nos/blob/main/docs/CONTRIBUTING.md before
opening a pull request. -->

<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->

## Summary

<!-- Please give a short summary of the change and the problem this
solves. -->

## Related issues

<!-- For example: "Closes #1234" -->

## Checks

- [ ] `make lint`: I've run `make lint` to lint the changes in this PR.
- [ ] `make test`: I've made sure the tests (`make test-cpu` or `make
test`) are passing.
- Additional tests:
   - [ ] Benchmark tests (when contributing new models)
   - [ ] GPU/HW tests

Various dev-ex improvements (runtime, logging etc) (#497)

## Summary
- Removed redundant `cudnn` dependencies (since Pytorch already ships
cudnn so's in `$CONDA_PREFIX/python3.8/site-packages/torch/lib`
- Removed system prompts from defaults to allow users more flexibility
- Added `mistralai/Mistral-7B-Instruct-v0.2` to llama chat
- Several log cleanup on startup for prettier demos
- Disabled ray usage stats and dashboard for now

## Related issues

<!-- For example: "Closes #1234" -->

## Checks

- [ ] `make lint`: I've run `make lint` to lint the changes in this PR.
- [ ] `make test`: I've made sure the tests (`make test-cpu` or `make
test`) are passing.
- Additional tests:
   - [ ] Benchmark tests (when contributing new models)
   - [ ] GPU/HW tests

Update roadmap (#485)

Quick update to add supported platforms to roadmap. Removes MacOS
install instructions for now.

## Checks

- [ ] `make lint`: I've run `make lint` to lint the changes in this PR.
- [ ] `make test`: I've made sure the tests (`make test-cpu` or `make
test`) are passing.
- Additional tests:
   - [ ] Benchmark tests (when contributing new models)
   - [ ] GPU/HW tests

Update SDXL example image (#483)

## Checks

- [x] `make lint`: I've run `make lint` to lint the changes in this PR.
- [x] `make test`: I've made sure the tests (`make test-cpu` or `make
test`) are passing.
- Additional tests:
   - [ ] Benchmark tests (when contributing new models)
   - [ ] GPU/HW tests

Release 0.1.0

Release 0.1.0rc3

Fix bug in twine upload (#454)

Incomplete flag in `create-pypi-release-loose` causing twine upload to
fail. Tested by reproducing the typo in the test flow and saw the same
error, so pretty confident this will get resolved.

- [ ] `make lint`: I've run `make lint` to lint the changes in this PR.
- [ ] `make test`: I've made sure the tests (`make test-cpu` or `make
test`) are passing.
- Additional tests:
   - [ ] Benchmark tests (when contributing new models)
   - [ ] GPU/HW tests