update llama_models.sku_list

llama_stack/cli/download.py

@@ -16,7 +16,6 @@ from pathlib import Path
 from typing import Dict, List, Optional
 
 import httpx
-from llama_models.sku_list import LlamaDownloadInfo
 from pydantic import BaseModel, ConfigDict
 from rich.console import Console
 from rich.progress import (
@@ -31,6 +30,7 @@ from termcolor import cprint
 
 from llama_stack.cli.subcommand import Subcommand
 from llama_stack.models.llama.datatypes import Model
+from llama_stack.models.llama.sku_list import LlamaDownloadInfo
 
 
 class Download(Subcommand):
@@ -454,7 +454,7 @@ def run_download_cmd(args: argparse.Namespace, parser: argparse.ArgumentParser):
         # Handle comma-separated model IDs
         model_ids = [model_id.strip() for model_id in args.model_id.split(",")]
 
-        from llama_models.sku_list import llama_meta_net_info, resolve_model
+        from llama_stack.models.llama.sku_list import llama_meta_net_info, resolve_model
 
         from .model.safety_models import (
             prompt_guard_download_info,

llama_stack/cli/model/describe.py

@@ -7,11 +7,11 @@
 import argparse
 import json
 
-from llama_models.sku_list import resolve_model
 from termcolor import colored
 
 from llama_stack.cli.subcommand import Subcommand
 from llama_stack.cli.table import print_table
+from llama_stack.models.llama.sku_list import resolve_model
 
 
 class ModelDescribe(Subcommand):

llama_stack/cli/model/list.py

@@ -6,10 +6,9 @@
 
 import argparse
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.cli.subcommand import Subcommand
 from llama_stack.cli.table import print_table
+from llama_stack.models.llama.sku_list import all_registered_models
 
 
 class ModelList(Subcommand):

llama_stack/cli/model/safety_models.py

@@ -6,10 +6,10 @@
 
 from typing import Any, Dict, Optional
 
-from llama_models.sku_list import LlamaDownloadInfo
 from pydantic import BaseModel, ConfigDict, Field
 
 from llama_stack.models.llama.datatypes import CheckpointQuantizationFormat, SamplingParams
+from llama_stack.models.llama.sku_list import LlamaDownloadInfo
 
 
 class PromptGuardModel(BaseModel):

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

@@ -30,7 +30,6 @@ 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 +46,7 @@ from llama_stack.models.llama.datatypes import (
     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

@@ -8,8 +8,6 @@ import asyncio
 import logging
 from typing import AsyncGenerator, List, Optional, Union
 
-from llama_models.sku_list import resolve_model
-
 from llama_stack.apis.common.content_types import (
     TextDelta,
     ToolCallDelta,
@@ -41,6 +39,7 @@ from llama_stack.models.llama.datatypes import (
     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

@@ -11,9 +11,9 @@ from typing import Any, Generator
 
 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 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

@@ -16,12 +16,12 @@ from fairscale.nn.model_parallel.layers import ColumnParallelLinear, RowParallel
 from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
 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/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

@@ -13,7 +13,6 @@
 from typing import Any, Callable, Dict
 
 import torch
-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 +23,7 @@ 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/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/remote/inference/groq/groq.py

@@ -9,7 +9,6 @@ from typing import AsyncIterator, List, Optional, Union
 
 import groq
 from groq import Groq
-from llama_models.sku_list import CoreModelId
 
 from llama_stack.apis.inference import (
     ChatCompletionRequest,
@@ -28,6 +27,7 @@ from llama_stack.apis.inference import (
 )
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
 from llama_stack.models.llama.datatypes import SamplingParams, ToolDefinition, ToolPromptFormat
+from llama_stack.models.llama.sku_list import CoreModelId
 from llama_stack.providers.remote.inference.groq.config import GroqConfig
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,

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

@@ -7,7 +7,6 @@
 import warnings
 from typing import AsyncIterator, List, Optional, Union
 
-from llama_models.sku_list import CoreModelId
 from openai import APIConnectionError, AsyncOpenAI
 
 from llama_stack.apis.inference import (
@@ -26,7 +25,7 @@ from llama_stack.apis.inference import (
     ToolChoice,
     ToolConfig,
 )
-from llama_stack.models.llama.datatypes import SamplingParams, ToolDefinition, ToolPromptFormat
+from llama_stack.models.llama.datatypes import CoreModelId, SamplingParams, ToolDefinition, ToolPromptFormat
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,
     build_model_alias,

llama_stack/providers/remote/inference/tgi/tgi.py

@@ -11,7 +11,6 @@ from typing import AsyncGenerator, List, Optional
 from huggingface_hub import AsyncInferenceClient, HfApi
 from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
-from llama_models.sku_list import all_registered_models
 
 from llama_stack.apis.common.content_types import InterleavedContent
 from llama_stack.apis.inference import (
@@ -31,6 +30,7 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.apis.models import Model
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -7,10 +7,9 @@ import json
 import logging
 from typing import AsyncGenerator, List, Optional, Union
 
-from llama_models.llama3.api import StopReason, ToolCall
+from llama_models.datatypes import StopReason, ToolCall
 from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
-from llama_models.sku_list import all_registered_models
 from openai import OpenAI
 
 from llama_stack.apis.common.content_types import InterleavedContent, TextDelta, ToolCallDelta, ToolCallParseStatus
@@ -37,6 +36,7 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.apis.models import Model, ModelType
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,

llama_stack/providers/tests/report.py

@@ -9,11 +9,11 @@ from collections import defaultdict
 from pathlib import Path
 
 import pytest
-from llama_models.sku_list import all_registered_models
 from pytest import ExitCode
 from pytest_html.basereport import _process_outcome
 
 from llama_stack.models.llama.datatypes import CoreModelId
+from llama_stack.models.llama.sku_list import all_registered_models
 
 INFERENCE_APIS = ["chat_completion"]
 FUNCTIONALITIES = ["streaming", "structured_output", "tool_calling"]

llama_stack/providers/utils/inference/__init__.py

@@ -6,9 +6,8 @@
 
 from typing import List
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.models.llama.datatypes import *  # noqa: F403
+from llama_stack.models.llama.sku_list import all_registered_models
 
 
 def is_supported_safety_model(model: Model) -> bool:

llama_stack/providers/utils/inference/model_registry.py

@@ -7,9 +7,8 @@
 from collections import namedtuple
 from typing import List, Optional
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.apis.models.models import ModelType
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
 from llama_stack.providers.utils.inference import (
     ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTOR,

llama_stack/providers/utils/inference/prompt_adapter.py

@@ -21,7 +21,6 @@ from llama_models.llama3.prompt_templates import (
     PythonListCustomToolGenerator,
     SystemDefaultGenerator,
 )
-from llama_models.sku_list import resolve_model
 from PIL import Image as PIL_Image
 
 from llama_stack.apis.common.content_types import (
@@ -52,6 +51,7 @@ from llama_stack.models.llama.datatypes import (
     ToolPromptFormat,
     is_multimodal,
 )
+from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.providers.utils.inference import supported_inference_models
 
 log = logging.getLogger(__name__)

llama_stack/templates/bedrock/bedrock.py

@@ -6,10 +6,9 @@
 
 from pathlib import Path
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.apis.models import ModelInput
 from llama_stack.distribution.datatypes import Provider, ToolGroupInput
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.remote.inference.bedrock.bedrock import MODEL_ALIASES
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings

llama_stack/templates/cerebras/cerebras.py

@@ -6,10 +6,9 @@
 
 from pathlib import Path
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.apis.models.models import ModelType
 from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )

llama_stack/templates/fireworks/fireworks.py

@@ -6,8 +6,6 @@
 
 from pathlib import Path
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.apis.models.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
@@ -15,6 +13,7 @@ from llama_stack.distribution.datatypes import (
     ShieldInput,
     ToolGroupInput,
 )
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )

llama_stack/templates/nvidia/nvidia.py

@@ -6,9 +6,8 @@
 
 from pathlib import Path
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
 from llama_stack.providers.remote.inference.nvidia.nvidia import _MODEL_ALIASES
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings

llama_stack/templates/sambanova/sambanova.py

@@ -6,14 +6,13 @@
 
 from pathlib import Path
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,
     ShieldInput,
     ToolGroupInput,
 )
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.remote.inference.sambanova import SambaNovaImplConfig
 from llama_stack.providers.remote.inference.sambanova.sambanova import MODEL_ALIASES
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings

llama_stack/templates/together/together.py

@@ -6,8 +6,6 @@
 
 from pathlib import Path
 
-from llama_models.sku_list import all_registered_models
-
 from llama_stack.apis.models.models import ModelType
 from llama_stack.distribution.datatypes import (
     ModelInput,
@@ -15,6 +13,7 @@ from llama_stack.distribution.datatypes import (
     ShieldInput,
     ToolGroupInput,
 )
+from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )