phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 02:44:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into register_custom_model

Browse source
This commit is contained in:
Rashmi Pawar 2025-04-16 14:35:51 +05:30 • committed by GitHub
commit afb792b9c1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
69 changed files with 8875 additions and 890 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -34,15 +34,18 @@ from llama_stack.apis.inference import (
ToolChoice,
ToolConfig,
)
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
from llama_stack.apis.models import Model, ModelType
from llama_stack.models.llama.datatypes import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.providers.utils.inference import (
ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTOR,
)
from llama_stack.apis.inference.inference import (
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAICompletion,
OpenAIMessageParam,
OpenAIResponseFormatParam,
)
from llama_stack.models.llama.datatypes import ToolPromptFormat
from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
)
@ -335,7 +338,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
n: Optional[int] = None,
parallel_tool_calls: Optional[bool] = None,
presence_penalty: Optional[float] = None,
response_format: Optional[Dict[str, str]] = None,
response_format: Optional[OpenAIResponseFormatParam] = None,
seed: Optional[int] = None,
stop: Optional[Union[str, List[str]]] = None,
stream: Optional[bool] = None,
@ -346,7 +349,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
top_logprobs: Optional[int] = None,
top_p: Optional[float] = None,
user: Optional[str] = None,
) -> OpenAIChatCompletion:
) -> Union[OpenAIChatCompletion, AsyncIterator[OpenAIChatCompletionChunk]]:
provider_model_id = self.get_provider_model_id(model)
params = await prepare_openai_completion_params(