test: Add VLLM provider support to integration tests (#2757)

- Add setup-vllm GitHub action to start VLLM container
- Extend integration test matrix to support both ollama and vllm
providers
- Make test setup conditional based on provider type
- Add provider-specific environment variables and configurations
- vllm tests setup to run weekly or can be triggered manually (only
ollama on PR)

TODO:
investigate failing tests for vllm provider (safety and post_training)
Also need a proper fix for #2713 (tmp fix for this in the first commit
in this PR)
Closes: #1648

---------

Signed-off-by: Derek Higgins <derekh@redhat.com>

tests/integration/inference/test_openai_completion.py

@@ -179,9 +179,7 @@ def test_openai_completion_prompt_logprobs(llama_stack_client, client_with_model
         model=text_model_id,
         prompt=prompt,
         stream=False,
-        extra_body={
-            "prompt_logprobs": prompt_logprobs,
-        },
+        prompt_logprobs=prompt_logprobs,
     )
     assert len(response.choices) > 0
     choice = response.choices[0]
@@ -196,9 +194,7 @@ def test_openai_completion_guided_choice(llama_stack_client, client_with_models,
         model=text_model_id,
         prompt=prompt,
         stream=False,
-        extra_body={
-            "guided_choice": ["joy", "sadness"],
-        },
+        guided_choice=["joy", "sadness"],
     )
     assert len(response.choices) > 0
     choice = response.choices[0]