feat: Add allow_listing_models

• Add allow_listing_models configuration flag to VLLM provider to control model listing behavior
• Implement allow_listing_models() method across all providers with default implementations in base classes
• Prevent HTTP requests to /v1/models endpoint when allow_listing_models=false for improved security and performance
• Fix unit tests to include allow_listing_models method in test classes and mock objects

llama_stack/distributions/ci-tests/run.yaml

@@ -31,6 +31,7 @@ providers:
       max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
       api_token: ${env.VLLM_API_TOKEN:=fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:=true}
+      allow_listing_models: ${env.VLLM_ALLOW_LISTING_MODELS:=true}
   - provider_id: ${env.TGI_URL:+tgi}
     provider_type: remote::tgi
     config:

llama_stack/distributions/postgres-demo/run.yaml

@@ -16,6 +16,7 @@ providers:
       max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
       api_token: ${env.VLLM_API_TOKEN:=fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:=true}
+      allow_listing_models: ${env.VLLM_ALLOW_LISTING_MODELS:=true}
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
   vector_io:

llama_stack/distributions/starter-gpu/run.yaml

@@ -31,6 +31,7 @@ providers:
       max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
       api_token: ${env.VLLM_API_TOKEN:=fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:=true}
+      allow_listing_models: ${env.VLLM_ALLOW_LISTING_MODELS:=true}
   - provider_id: ${env.TGI_URL:+tgi}
     provider_type: remote::tgi
     config:

llama_stack/distributions/starter/run.yaml

@@ -31,6 +31,7 @@ providers:
       max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
       api_token: ${env.VLLM_API_TOKEN:=fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:=true}
+      allow_listing_models: ${env.VLLM_ALLOW_LISTING_MODELS:=true}
   - provider_id: ${env.TGI_URL:+tgi}
     provider_type: remote::tgi
     config: