GitLab

Co-authored-by: hongkuan <hongkuanz@nvidia.com>

feat: rename dynamo-sdk to dynamo; add dynamo run to call dynamo-run under the hood for unification (#104)

In https://github.com/ai-dynamo/dynamo/pull/89 `dynamo-run` was moved into a workspace. That means it builds in that workspace, so into `launch/target` not `launch/dynamo-run/target`.

Update docs to match.

If the python file raises an exception we print it like Python would.

```
$ ./target/debug/dynamo-run in=http out=pystr:~/Temp/cn47/1_e.py --model-name test

Traceback (most recent call last):
  File "/home/graham/Temp/cn47/1_e.py", line 17, in generate
    raise MyException("The message")
1_e.MyException: The message
```

Co-authored-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Alec <35311602+alec-flowers@users.noreply.github.com>

- Latest from repo, many improvements
- Support most of the OpenAI request features (temperature, top_p, etc)
- Download models from Hugging Face if necessary

Co-authored-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>

Co-authored-by: hongkuanz <hongkuanz@nvidia.com>

Co-authored-by: hongkuanz <hongkuanz@nvidia.com>

Co-authored-by: hongkuanz <hongkuanz@nvidia.com>

Co-authored-by: Shreyas Misra <shreyasm@nvidia.com>

For the `echo` and `pystr` engines we previously required the user to pass `--model-name <x>` so we would have a name for the model. If the input is HTTP we do need this to match on the users' JSON request.

If the input is Text we don't need a name. So if the input is Text and we don't already have a name for the model, give it one.

Co-authored-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>