feat: add dynamic model registration support to TGI inference (#3417)

# What does this PR do?

adds dynamic model support to TGI

add new overwrite_completion_id feature to OpenAIMixin to deal with TGI
always returning id=""

## Test Plan

tgi: `docker run --gpus all --shm-size 1g -p 8080:80 -v /data:/data
ghcr.io/huggingface/text-generation-inference --model-id
Qwen/Qwen3-0.6B`

stack: `TGI_URL=http://localhost:8080 uv run llama stack build
--image-type venv --distro ci-tests --run`

test: `./scripts/integration-tests.sh --stack-config
http://localhost:8321 --setup tgi --subdirs inference --pattern openai`

tests/integration/inference/test_openai_completion.py

@@ -48,7 +48,6 @@ def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id)
         "remote::nvidia",
         "remote::runpod",
         "remote::sambanova",
-        "remote::tgi",
         "remote::vertexai",
         # {"error":{"message":"Unknown request URL: GET /openai/v1/completions. Please check the URL for typos,
         # or see the docs at https://console.groq.com/docs/","type":"invalid_request_error","code":"unknown_url"}}
@@ -96,6 +95,7 @@ def skip_if_doesnt_support_n(client_with_models, model_id):
         "remote::vertexai",
         #  Error code: 400 - [{'error': {'code': 400, 'message': 'Unable to submit request because candidateCount must be 1 but
         #  the entered value was 2. Update the candidateCount value and try again.', 'status': 'INVALID_ARGUMENT'}
+        "remote::tgi",  # TGI ignores n param silently
     ):
         pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support n param.")
 
@@ -110,7 +110,6 @@ def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, mode
         "remote::cerebras",
         "remote::databricks",
         "remote::runpod",
-        "remote::tgi",
     ):
         pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI chat completions.")