phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 06:28:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 5115801835 into 537dc693ee

Browse source
This commit is contained in:
Mustafa Elbehery 2025-07-24 19:26:53 +02:00 • committed by GitHub
commit 55c415f64c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
49 changed files with 307 additions and 97 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/llama_openai_compat/llama.py
View file

@ -3,15 +3,14 @@
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import logging
from llama_stack.log import get_logger
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from .models import MODEL_ENTRIES
logger = logging.getLogger(__name__)
logger = get_logger(name=__name__, category="core")
class LlamaCompatInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):

4
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -4,7 +4,6 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import logging
import warnings
from collections.abc import AsyncIterator
@ -33,6 +32,7 @@ from llama_stack.apis.inference import (
ToolChoice,
ToolConfig,
)
from llama_stack.log import get_logger
from llama_stack.models.llama.datatypes import ToolDefinition, ToolPromptFormat
from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
@ -54,7 +54,7 @@ from .openai_utils import (
)
from .utils import _is_nvidia_hosted
logger = logging.getLogger(__name__)
logger = get_logger(name=__name__, category="core")
class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):

6
llama_stack/providers/remote/inference/nvidia/utils.py
View file

@ -4,13 +4,13 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import logging
import httpx
from llama_stack.log import get_logger
from . import NVIDIAConfig
logger = logging.getLogger(__name__)
logger = get_logger(name=__name__, category="core")
def _is_nvidia_hosted(config: NVIDIAConfig) -> bool:

5
llama_stack/providers/remote/inference/openai/openai.py
View file

@ -4,15 +4,14 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import logging
from llama_stack.log import get_logger
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from .config import OpenAIConfig
from .models import MODEL_ENTRIES
logger = logging.getLogger(__name__)
logger = get_logger(name=__name__, category="core")
#

4
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
import logging
from collections.abc import AsyncGenerator
from huggingface_hub import AsyncInferenceClient, HfApi
@ -34,6 +33,7 @@ from llama_stack.apis.inference import (
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.log import get_logger
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 (
@ -58,7 +58,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
log = logging.getLogger(__name__)
log = get_logger(name=__name__, category="core")
def build_hf_repo_model_entries():