GitLab

This lets us do:
```
dynamo-run out=llamacpp <gguf_file>
```

Previously a `--model-config <hf-repo>` was also required, to configure our tokenizer.

On Mac embedded python interpreters don't pick up the virtual env. This seems to be a known problem. Fix the sys.path.

Needs more testing but good enough for now. I get the same results with this as with `vllm serve`.

triton-distributed-llm component and support in tio