Merge remote-tracking branch 'mattf/add-nvidia-inference-adapter' into cdgamarose/add_nvidia_distro

llama_stack/templates/fireworks/run.yaml

@@ -57,11 +57,11 @@ models:
   provider_id: null
   provider_model_id: fireworks/llama-v3p1-405b-instruct
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
+  model_id: meta-llama/Llama-3.2-1B-Instruct
   provider_id: null
   provider_model_id: fireworks/llama-v3p2-1b-instruct
 - metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  model_id: meta-llama/Llama-3.2-3B-Instruct
   provider_id: null
   provider_model_id: fireworks/llama-v3p2-3b-instruct
 - metadata: {}

llama_stack/templates/tgi/build.yaml

@@ -2,7 +2,7 @@ version: '2'
 name: tgi
 distribution_spec:
   description: Use (an external) TGI server for running LLM inference
-  docker_image: llamastack/distribution-tgi:test-0.0.52rc3
+  docker_image: null
   providers:
     inference:
     - remote::tgi

llama_stack/templates/tgi/run-with-safety.yaml

@@ -1,6 +1,6 @@
 version: '2'
 image_name: tgi
-docker_image: llamastack/distribution-tgi:test-0.0.52rc3
+docker_image: null
 conda_env: tgi
 apis:
 - agents

llama_stack/templates/tgi/run.yaml

@@ -1,6 +1,6 @@
 version: '2'
 image_name: tgi
-docker_image: llamastack/distribution-tgi:test-0.0.52rc3
+docker_image: null
 conda_env: tgi
 apis:
 - agents

llama_stack/templates/tgi/tgi.py

@@ -41,7 +41,7 @@ def get_distribution_template() -> DistributionTemplate:
         name="tgi",
         distro_type="self_hosted",
         description="Use (an external) TGI server for running LLM inference",
-        docker_image="llamastack/distribution-tgi:test-0.0.52rc3",
+        docker_image=None,
         template_path=Path(__file__).parent / "doc_template.md",
         providers=providers,
         default_models=[inference_model, safety_model],