chore: add meta/llama-3.3-70b-instruct as supported nvidia inference provider model (#1985)

see https://build.nvidia.com/meta/llama-3_3-70b-instruct

docs/source/distributions/self_hosted_distro/nvidia.md

@@ -45,6 +45,7 @@ The following models are available by default:
 - `meta/llama-3.2-3b-instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
 - `meta/llama-3.2-11b-vision-instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
 - `meta/llama-3.2-90b-vision-instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
+- `meta/llama-3.3-70b-instruct (aliases: meta-llama/Llama-3.3-70B-Instruct)`
 - `nvidia/llama-3.2-nv-embedqa-1b-v2 `
 - `nvidia/nv-embedqa-e5-v5 `
 - `nvidia/nv-embedqa-mistral-7b-v2 `

llama_stack/providers/remote/inference/nvidia/models.py

@@ -48,6 +48,10 @@ MODEL_ENTRIES = [
         "meta/llama-3.2-90b-vision-instruct",
         CoreModelId.llama3_2_90b_vision_instruct.value,
     ),
+    build_hf_repo_model_entry(
+        "meta/llama-3.3-70b-instruct",
+        CoreModelId.llama3_3_70b_instruct.value,
+    ),
     # NeMo Retriever Text Embedding models -
     #
     # https://docs.nvidia.com/nim/nemo-retriever/text-embedding/latest/support-matrix.html

llama_stack/templates/nvidia/run.yaml

@@ -173,6 +173,16 @@ models:
   provider_id: nvidia
   provider_model_id: meta/llama-3.2-90b-vision-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.3-70b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.3-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.3-70b-instruct
+  model_type: llm
 - metadata:
     embedding_dimension: 2048
     context_length: 8192