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/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