phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

ModelAlias -> ProviderModelEntry

Browse source
This commit is contained in:
Ashwin Bharambe 2025-02-20 14:02:36 -08:00
parent 561295af76
commit 07ccf908f7
27 changed files with 132 additions and 132 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/providers/remote/inference/nvidia/models.py
View file

@ -6,43 +6,43 @@
from llama_stack.models.llama.datatypes import CoreModelId
from llama_stack.providers.utils.inference.model_registry import (
build_hf_repo_model_alias,
build_hf_repo_model_entry,
)
_MODEL_ALIASES = [
build_hf_repo_model_alias(
_MODEL_ENTRIES = [
build_hf_repo_model_entry(
"meta/llama3-8b-instruct",
CoreModelId.llama3_8b_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama3-70b-instruct",
CoreModelId.llama3_70b_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama-3.1-8b-instruct",
CoreModelId.llama3_1_8b_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama-3.1-70b-instruct",
CoreModelId.llama3_1_70b_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama-3.1-405b-instruct",
CoreModelId.llama3_1_405b_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama-3.2-1b-instruct",
CoreModelId.llama3_2_1b_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama-3.2-3b-instruct",
CoreModelId.llama3_2_3b_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama-3.2-11b-vision-instruct",
CoreModelId.llama3_2_11b_vision_instruct.value,
),
build_hf_repo_model_alias(
build_hf_repo_model_entry(
"meta/llama-3.2-90b-vision-instruct",
CoreModelId.llama3_2_90b_vision_instruct.value,
),

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

@ -33,7 +33,7 @@ from llama_stack.providers.utils.inference.model_registry import (
from llama_stack.providers.utils.inference.prompt_adapter import content_has_media
from . import NVIDIAConfig
from .models import _MODEL_ALIASES
from .models import _MODEL_ENTRIES
from .openai_utils import (
convert_chat_completion_request,
convert_completion_request,
@ -50,7 +50,7 @@ logger = logging.getLogger(__name__)
class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
def __init__(self, config: NVIDIAConfig) -> None:
# TODO(mf): filter by available models
ModelRegistryHelper.__init__(self, model_aliases=_MODEL_ALIASES)
ModelRegistryHelper.__init__(self, model_entries=_MODEL_ENTRIES)
logger.info(f"Initializing NVIDIAInferenceAdapter({config.url})...")