cannot import name 'GreedySamplingStrategy' (#806)

# What does this PR do?

Fixes error when running an provider using openai_compat.py

```python
Traceback (most recent call last):
  File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/server/server.py", line 426, in <module>
    main()
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/server/server.py", line 349, in main
    impls = asyncio.run(construct_stack(config))
  File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/asyncio/runners.py", line 44, in run
    return loop.run_until_complete(main)
  File "/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
    return future.result()
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/stack.py", line 207, in construct_stack
    impls = await resolve_impls(
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/resolver.py", line 239, in resolve_impls
    impl = await instantiate_provider(
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/distribution/resolver.py", line 330, in instantiate_provider
    impl = await fn(*args)
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/providers/remote/inference/vllm/__init__.py", line 11, in get_adapter_impl
    from .vllm import VLLMInferenceAdapter
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/providers/remote/inference/vllm/vllm.py", line 39, in <module>
    from llama_stack.providers.utils.inference.openai_compat import (
  File "/home/ubuntu/us-south-2/llama-stack/llama_stack/providers/utils/inference/openai_compat.py", line 11, in <module>
    from llama_models.llama3.api.datatypes import (
ImportError: cannot import name 'GreedySamplingStrategy' from 'llama_models.llama3.api.datatypes' (/home/ubuntu/miniconda3/envs/llamastack-vllm/lib/python3.10/site-packages/llama_models/llama3/api/datatypes.py)
++ error_handler 61
++ echo 'Error occurred in script at line: 61'
Error occurred in script at line: 61
++ exit 1
```

## Test Plan

```bash
conda create --name llamastack-vllm python=3.10
conda activate llamastack-vllm

# To sync with the current llama-models repo
pip install -e git+https://github.com/meta-llama/llama-models.git#egg=llama-models

export INFERENCE_MODEL=unsloth/Llama-3.3-70B-Instruct-bnb-4bit && \
pip install -e . && \
llama stack build --template remote-vllm --image-type conda && \
llama stack run ./distributions/remote-vllm/run.yaml \
  --port 5000 \
  --env INFERENCE_MODEL=$INFERENCE_MODEL \
  --env VLLM_URL=http://localhost:8000
```

## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [x] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

llama_stack/providers/utils/inference/openai_compat.py

@@ -6,15 +6,15 @@
 
 from typing import AsyncGenerator, Dict, List, Optional
 
-from llama_models.llama3.api.chat_format import ChatFormat
+from llama_models.datatypes import (
-
-from llama_models.llama3.api.datatypes import (
     GreedySamplingStrategy,
     SamplingParams,
-    StopReason,
     TopKSamplingStrategy,
     TopPSamplingStrategy,
 )
+
+from llama_models.llama3.api.chat_format import ChatFormat
+from llama_models.llama3.api.datatypes import StopReason
 from pydantic import BaseModel
 
 from llama_stack.apis.common.content_types import (