feat(providers): sambanova updated to use LiteLLM openai-compat (#1596)

# What does this PR do? switch sambanova inference adaptor to LiteLLM usage to simplify integration and solve issues with current adaptor when streaming and tool calling, models and templates updated ## Test Plan pytest -s -v tests/integration/inference/test_text_inference.py --stack-config=sambanova --text-model=sambanova/Meta-Llama-3.3-70B-Instruct pytest -s -v tests/integration/inference/test_vision_inference.py --stack-config=sambanova --vision-model=sambanova/Llama-3.2-11B-Vision-Instruct
2025-06-27 18:50:41 +00:00 · 2025-05-06 18:50:22 -05:00 · 2025-05-06 18:50:22 -05:00 · b2b00a216b
commit b2b00a216b
parent dd49ef31f1
15 changed files with 529 additions and 404 deletions
--- a/llama_stack/templates/dependencies.json
+++ b/llama_stack/templates/dependencies.json
@ -619,10 +619,11 @@
    "fastapi",
    "fire",
    "httpx",
+    "litellm",
    "matplotlib",
+    "mcp",
    "nltk",
    "numpy",
-    "openai",
    "opentelemetry-exporter-otlp-proto-http",
    "opentelemetry-sdk",
    "pandas",
@ -637,7 +638,9 @@
    "sentencepiece",
    "tqdm",
    "transformers",
-    "uvicorn"
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
  ],
  "tgi": [
    "aiohttp",
--- a/llama_stack/templates/dev/build.yaml
+++ b/llama_stack/templates/dev/build.yaml
@ -8,6 +8,7 @@ distribution_spec:
    - remote::anthropic
    - remote::gemini
    - remote::groq
+    - remote::sambanova
    - inline::sentence-transformers
    vector_io:
    - inline::sqlite-vec
--- a/llama_stack/templates/dev/dev.py
+++ b/llama_stack/templates/dev/dev.py
@ -38,6 +38,10 @@ from llama_stack.providers.remote.inference.openai.config import OpenAIConfig
 from llama_stack.providers.remote.inference.openai.models import (
    MODEL_ENTRIES as OPENAI_MODEL_ENTRIES,
 )
+from llama_stack.providers.remote.inference.sambanova.config import SambaNovaImplConfig
+from llama_stack.providers.remote.inference.sambanova.models import (
+    MODEL_ENTRIES as SAMBANOVA_MODEL_ENTRIES,
+)
 from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
 from llama_stack.providers.remote.vector_io.pgvector.config import (
    PGVectorVectorIOConfig,
@ -77,6 +81,11 @@ def get_inference_providers() -> tuple[list[Provider], list[ModelInput]]:
            GROQ_MODEL_ENTRIES,
            GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:}"),
        ),
+        (
+            "sambanova",
+            SAMBANOVA_MODEL_ENTRIES,
+            SambaNovaImplConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:}"),
+        ),
    ]
    inference_providers = []
    available_models = {}
--- a/llama_stack/templates/dev/run.yaml
+++ b/llama_stack/templates/dev/run.yaml
@ -34,6 +34,11 @@ providers:
    config:
      url: https://api.groq.com
      api_key: ${env.GROQ_API_KEY:}
+  - provider_id: sambanova
+    provider_type: remote::sambanova
+    config:
+      url: https://api.sambanova.ai/v1
+      api_key: ${env.SAMBANOVA_API_KEY:}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
    config: {}
@ -413,6 +418,106 @@ models:
  provider_id: groq
  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-3.1-8B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-3.1-405B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-3.2-1B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-1B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-3.2-3B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-3.3-70B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Llama-3.2-11B-Vision-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Llama-3.2-90B-Vision-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-Guard-3-8B
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-8B
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
+  model_type: llm
 - metadata:
    embedding_dimension: 384
  model_id: all-MiniLM-L6-v2
--- a/llama_stack/templates/sambanova/build.yaml
+++ b/llama_stack/templates/sambanova/build.yaml
@ -1,9 +1,10 @@
 version: '2'
 distribution_spec:
-  description: Use SambaNova.AI for running LLM inference
+  description: Use SambaNova for running LLM inference
  providers:
    inference:
    - remote::sambanova
+    - inline::sentence-transformers
    vector_io:
    - inline::faiss
    - remote::chromadb
@ -18,4 +19,6 @@ distribution_spec:
    - remote::brave-search
    - remote::tavily-search
    - inline::rag-runtime
+    - remote::model-context-protocol
+    - remote::wolfram-alpha
 image_type: conda
--- a/llama_stack/templates/sambanova/run.yaml
+++ b/llama_stack/templates/sambanova/run.yaml
@ -14,6 +14,9 @@ providers:
    config:
      url: https://api.sambanova.ai/v1
      api_key: ${env.SAMBANOVA_API_KEY}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
  vector_io:
  - provider_id: faiss
    provider_type: inline::faiss
@ -68,110 +71,122 @@ providers:
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
+  - provider_id: wolfram-alpha
+    provider_type: remote::wolfram-alpha
+    config:
+      api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
 metadata_store:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/registry.db
 models:
 - metadata: {}
-  model_id: Meta-Llama-3.1-8B-Instruct
+  model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.1-8B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.1-8B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.1-8B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.1-70B-Instruct
+  model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.1-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.1-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: Meta-Llama-3.1-405B-Instruct
-  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.1-405B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.1-405B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.2-1B-Instruct
+  model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.2-1B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-1B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.2-1B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.2-3B-Instruct
+  model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.2-3B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-3B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.2-3B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.3-70B-Instruct
+  model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.3-70B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.3-70B-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-3.3-70B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Llama-3.2-11B-Vision-Instruct
+  model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  provider_id: sambanova
-  provider_model_id: Llama-3.2-11B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
  provider_id: sambanova
-  provider_model_id: Llama-3.2-11B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Llama-3.2-90B-Vision-Instruct
+  model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  provider_id: sambanova
-  provider_model_id: Llama-3.2-90B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
  provider_id: sambanova
-  provider_model_id: Llama-3.2-90B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-Guard-3-8B
+  model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
  provider_id: sambanova
-  provider_model_id: Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: sambanova
-  provider_model_id: Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: Llama-4-Scout-17B-16E-Instruct
-  provider_id: sambanova
-  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: sambanova
-  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
  model_type: llm
+- metadata: {}
+  model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: sambanova
+  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-Guard-3-8B
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-8B
+  provider_id: sambanova
+  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  model_type: embedding
 shields:
 - shield_id: meta-llama/Llama-Guard-3-8B
 vector_dbs: []
@ -183,5 +198,7 @@ tool_groups:
  provider_id: tavily-search
 - toolgroup_id: builtin::rag
  provider_id: rag-runtime
+- toolgroup_id: builtin::wolfram_alpha
+  provider_id: wolfram-alpha
 server:
  port: 8321
--- a/llama_stack/templates/sambanova/sambanova.py
+++ b/llama_stack/templates/sambanova/sambanova.py
@ -6,7 +6,16 @@

 from pathlib import Path

-from llama_stack.distribution.datatypes import Provider, ShieldInput, ToolGroupInput
+from llama_stack.apis.models.models import ModelType
+from llama_stack.distribution.datatypes import (
+    ModelInput,
+    Provider,
+    ShieldInput,
+    ToolGroupInput,
+)
+from llama_stack.providers.inline.inference.sentence_transformers import (
+    SentenceTransformersInferenceConfig,
+)
 from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.remote.inference.sambanova import SambaNovaImplConfig
 from llama_stack.providers.remote.inference.sambanova.models import MODEL_ENTRIES
@ -23,7 +32,7 @@ from llama_stack.templates.template import (

 def get_distribution_template() -> DistributionTemplate:
    providers = {
-        "inference": ["remote::sambanova"],
+        "inference": ["remote::sambanova", "inline::sentence-transformers"],
        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
        "safety": ["inline::llama-guard"],
        "agents": ["inline::meta-reference"],
@ -32,16 +41,29 @@ def get_distribution_template() -> DistributionTemplate:
            "remote::brave-search",
            "remote::tavily-search",
            "inline::rag-runtime",
+            "remote::model-context-protocol",
+            "remote::wolfram-alpha",
        ],
    }
    name = "sambanova"
-
    inference_provider = Provider(
        provider_id=name,
        provider_type=f"remote::{name}",
        config=SambaNovaImplConfig.sample_run_config(),
    )
-
+    embedding_provider = Provider(
+        provider_id="sentence-transformers",
+        provider_type="inline::sentence-transformers",
+        config=SentenceTransformersInferenceConfig.sample_run_config(),
+    )
+    embedding_model = ModelInput(
+        model_id="all-MiniLM-L6-v2",
+        provider_id="sentence-transformers",
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dimension": 384,
+        },
+    )
    vector_io_providers = [
        Provider(
            provider_id="faiss",
@ -79,23 +101,27 @@ def get_distribution_template() -> DistributionTemplate:
            toolgroup_id="builtin::rag",
            provider_id="rag-runtime",
        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::wolfram_alpha",
+            provider_id="wolfram-alpha",
+        ),
    ]

    return DistributionTemplate(
        name=name,
        distro_type="self_hosted",
-        description="Use SambaNova.AI for running LLM inference",
-        docker_image=None,
+        description="Use SambaNova for running LLM inference",
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        available_models_by_provider=available_models,
        run_configs={
            "run.yaml": RunConfigSettings(
                provider_overrides={
-                    "inference": [inference_provider],
+                    "inference": [inference_provider, embedding_provider],
                    "vector_io": vector_io_providers,
                },
-                default_models=default_models,
+                default_models=default_models + [embedding_model],
                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
                default_tool_groups=default_tool_groups,
            ),
@ -107,7 +133,7 @@ def get_distribution_template() -> DistributionTemplate:
            ),
            "SAMBANOVA_API_KEY": (
                "",
-                "SambaNova.AI API Key",
+                "SambaNova API Key",
            ),
        },
    )
--- a/llama_stack/templates/verification/run.yaml
+++ b/llama_stack/templates/verification/run.yaml
@ -502,104 +502,104 @@ models:
  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.1-8B-Instruct
+  model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.1-8B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.1-8B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.1-8B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.1-70B-Instruct
+  model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.1-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.1-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: Meta-Llama-3.1-405B-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.1-405B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.1-405B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.2-1B-Instruct
+  model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.2-1B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-1B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.2-1B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.2-3B-Instruct
+  model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.2-3B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-3B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.2-3B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-3.3-70B-Instruct
+  model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.3-70B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.3-70B-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-3.3-70B-Instruct
+  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Llama-3.2-11B-Vision-Instruct
+  model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Llama-3.2-11B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Llama-3.2-11B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Llama-3.2-90B-Vision-Instruct
+  model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Llama-3.2-90B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Llama-3.2-90B-Vision-Instruct
+  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
  model_type: llm
 - metadata: {}
-  model_id: Meta-Llama-Guard-3-8B
+  model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: sambanova-openai-compat
-  provider_model_id: Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: Llama-4-Scout-17B-16E-Instruct
-  provider_id: sambanova-openai-compat
-  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
  model_type: llm
 - metadata: {}
  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
  provider_id: sambanova-openai-compat
-  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: sambanova/Meta-Llama-Guard-3-8B
+  provider_id: sambanova-openai-compat
+  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-8B
+  provider_id: sambanova-openai-compat
+  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
  model_type: llm
 - metadata: {}
  model_id: llama3.1-8b