chore: move all Llama Stack types from llama-models to llama-stack (#1098)

llama-models should have extremely minimal cruft. Its sole purpose
should be didactic -- show the simplest implementation of the llama
models and document the prompt formats, etc.

This PR is the complement to
https://github.com/meta-llama/llama-models/pull/279

## Test Plan

Ensure all `llama` CLI `model` sub-commands work:

```bash
llama model list
llama model download --model-id ...
llama model prompt-format -m ...
```

Ran tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/
LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/
LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/
```

Create a fresh venv `uv venv && source .venv/bin/activate` and run
`llama stack build --template fireworks --image-type venv` followed by
`llama stack run together --image-type venv` <-- the server runs

Also checked that the OpenAPI generator can run and there is no change
in the generated files as a result.

```bash
cd docs/openapi_generator
sh run_openapi_generator.sh
```

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -17,7 +17,6 @@ from typing import Any, AsyncGenerator, Dict, List, Optional, Tuple
 from urllib.parse import urlparse
 
 import httpx
-from llama_models.llama3.api.datatypes import BuiltinTool, ToolCall, ToolParamDefinition
 from pydantic import TypeAdapter
 
 from llama_stack.apis.agents import (
@@ -63,6 +62,7 @@ from llama_stack.apis.inference import (
 from llama_stack.apis.safety import Safety
 from llama_stack.apis.tools import RAGDocument, RAGQueryConfig, ToolGroups, ToolRuntime
 from llama_stack.apis.vector_io import VectorIO
+from llama_stack.models.llama.datatypes import BuiltinTool, ToolCall, ToolParamDefinition
 from llama_stack.providers.utils.kvstore import KVStore
 from llama_stack.providers.utils.memory.vector_store import concat_interleaved_content
 from llama_stack.providers.utils.telemetry import tracing

llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py

@@ -8,7 +8,6 @@ import tempfile
 from typing import AsyncIterator, List, Optional, Union
 
 import pytest
-from llama_models.llama3.api.datatypes import BuiltinTool
 
 from llama_stack.apis.agents import (
     AgentConfig,
@@ -41,6 +40,7 @@ from llama_stack.apis.tools import (
     ToolInvocationResult,
 )
 from llama_stack.apis.vector_io import QueryChunksResponse
+from llama_stack.models.llama.datatypes import BuiltinTool
 from llama_stack.providers.inline.agents.meta_reference.agent_instance import (
     MEMORY_QUERY_TOOL,
 )

llama_stack/providers/inline/inference/meta_reference/generation.py

@@ -23,20 +23,13 @@ from fairscale.nn.model_parallel.initialize import (
     initialize_model_parallel,
     model_parallel_is_initialized,
 )
-from llama_models.datatypes import (
-    GreedySamplingStrategy,
-    SamplingParams,
-    TopPSamplingStrategy,
-)
 from llama_models.llama3.api.args import ModelArgs
 from llama_models.llama3.api.chat_format import ChatFormat, LLMInput
-from llama_models.llama3.api.datatypes import Model
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.llama3.reference_impl.model import Transformer
 from llama_models.llama3.reference_impl.multimodal.model import (
     CrossAttentionTransformer,
 )
-from llama_models.sku_list import resolve_model
 from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
 from pydantic import BaseModel
 
@@ -47,6 +40,13 @@ from llama_stack.apis.inference import (
     ResponseFormatType,
 )
 from llama_stack.distribution.utils.model_utils import model_local_dir
+from llama_stack.models.llama.datatypes import (
+    GreedySamplingStrategy,
+    Model,
+    SamplingParams,
+    TopPSamplingStrategy,
+)
+from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.providers.utils.inference.prompt_adapter import (
     ChatCompletionRequestWithRawContent,
     CompletionRequestWithRawContent,

llama_stack/providers/inline/inference/meta_reference/inference.py

@@ -8,14 +8,6 @@ import asyncio
 import logging
 from typing import AsyncGenerator, List, Optional, Union
 
-from llama_models.llama3.api.datatypes import (
-    SamplingParams,
-    StopReason,
-    ToolDefinition,
-    ToolPromptFormat,
-)
-from llama_models.sku_list import resolve_model
-
 from llama_stack.apis.common.content_types import (
     TextDelta,
     ToolCallDelta,
@@ -41,6 +33,13 @@ from llama_stack.apis.inference import (
     ToolConfig,
 )
 from llama_stack.apis.models import Model, ModelType
+from llama_stack.models.llama.datatypes import (
+    SamplingParams,
+    StopReason,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.embedding_mixin import (
     SentenceTransformerEmbeddingMixin,

llama_stack/providers/inline/inference/meta_reference/model_parallel.py

@@ -10,10 +10,10 @@ from functools import partial
 from typing import Any, Generator
 
 from llama_models.llama3.api.chat_format import ChatFormat
-from llama_models.llama3.api.datatypes import Model
 from llama_models.llama3.api.tokenizer import Tokenizer
-from llama_models.sku_list import resolve_model
 
+from llama_stack.models.llama.datatypes import Model
+from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.providers.utils.inference.prompt_adapter import (
     ChatCompletionRequestWithRawContent,
     CompletionRequestWithRawContent,

llama_stack/providers/inline/inference/meta_reference/quantization/loader.py

@@ -14,14 +14,14 @@ from typing import Any, Dict, List, Optional
 import torch
 from fairscale.nn.model_parallel.layers import ColumnParallelLinear, RowParallelLinear
 from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
-from llama_models.datatypes import CheckpointQuantizationFormat
 from llama_models.llama3.api.args import ModelArgs
 from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
-from llama_models.sku_list import resolve_model
 from torch import Tensor, nn
 from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
 
 from llama_stack.apis.inference import QuantizationType
+from llama_stack.models.llama.datatypes import CheckpointQuantizationFormat
+from llama_stack.models.llama.sku_list import resolve_model
 
 from ..config import MetaReferenceQuantizedInferenceConfig
 

llama_stack/providers/inline/inference/vllm/config.py

@@ -4,10 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_models.schema_utils import json_schema_type
 from pydantic import BaseModel, Field, field_validator
 
 from llama_stack.providers.utils.inference import supported_inference_models
+from llama_stack.schema_utils import json_schema_type
 
 
 @json_schema_type

llama_stack/providers/inline/inference/vllm/vllm.py

@@ -11,7 +11,6 @@ from typing import AsyncGenerator, List, Optional
 
 from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
-from llama_models.sku_list import resolve_model
 from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.engine.async_llm_engine import AsyncLLMEngine
 from vllm.sampling_params import SamplingParams as VLLMSamplingParams
@@ -35,6 +34,7 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.apis.models import Model
+from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import (
     OpenAICompatCompletionChoice,

llama_stack/providers/inline/post_training/torchtune/common/utils.py

@@ -13,8 +13,6 @@
 from typing import Any, Callable, Dict
 
 import torch
-from llama_models.datatypes import Model
-from llama_models.sku_list import resolve_model
 from pydantic import BaseModel
 from torchtune.data._messages import InputOutputToMessages, ShareGPTToMessages
 from torchtune.models.llama3 import llama3_tokenizer
@@ -24,6 +22,8 @@ from torchtune.models.llama3_2 import lora_llama3_2_3b
 from torchtune.modules.transforms import Transform
 
 from llama_stack.apis.post_training import DatasetFormat
+from llama_stack.models.llama.datatypes import Model
+from llama_stack.models.llama.sku_list import resolve_model
 
 
 class ModelConfig(BaseModel):

llama_stack/providers/inline/post_training/torchtune/post_training.py

@@ -6,8 +6,6 @@
 from datetime import datetime
 from typing import Any, Dict, Optional
 
-from llama_models.schema_utils import webmethod
-
 from llama_stack.apis.datasetio import DatasetIO
 from llama_stack.apis.datasets import Datasets
 from llama_stack.apis.post_training import (
@@ -27,6 +25,7 @@ from llama_stack.providers.inline.post_training.torchtune.config import (
 from llama_stack.providers.inline.post_training.torchtune.recipes.lora_finetuning_single_device import (
     LoraFinetuningSingleDevice,
 )
+from llama_stack.schema_utils import webmethod
 
 
 class TorchtunePostTrainingImpl:

llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py

@@ -14,7 +14,6 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
 import torch
-from llama_models.sku_list import resolve_model
 from torch import nn
 from torch.optim import Optimizer
 from torch.utils.data import DataLoader, DistributedSampler
@@ -46,6 +45,7 @@ from llama_stack.apis.post_training import (
 )
 from llama_stack.distribution.utils.config_dirs import DEFAULT_CHECKPOINT_DIR
 from llama_stack.distribution.utils.model_utils import model_local_dir
+from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.providers.inline.post_training.common.validator import (
     validate_input_dataset_schema,
 )

llama_stack/providers/inline/safety/llama_guard/llama_guard.py

@@ -8,9 +8,6 @@ import re
 from string import Template
 from typing import Any, Dict, List, Optional
 
-from llama_models.datatypes import CoreModelId
-from llama_models.llama3.api.datatypes import Role
-
 from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
 from llama_stack.apis.inference import (
     ChatCompletionResponseEventType,
@@ -26,6 +23,7 @@ from llama_stack.apis.safety import (
 )
 from llama_stack.apis.shields import Shield
 from llama_stack.distribution.datatypes import Api
+from llama_stack.models.llama.datatypes import CoreModelId, Role
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,

llama_stack/providers/inline/vector_io/faiss/config.py

@@ -6,13 +6,13 @@
 
 from typing import Any, Dict
 
-from llama_models.schema_utils import json_schema_type
 from pydantic import BaseModel
 
 from llama_stack.providers.utils.kvstore.config import (
     KVStoreConfig,
     SqliteKVStoreConfig,
 )
+from llama_stack.schema_utils import json_schema_type
 
 
 @json_schema_type