phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 18:43:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into feat/litellm_sambanova_usage

Browse source
This commit is contained in:
jhpiedrahitao 2025-04-01 07:57:21 -05:00
commit 9c9f9577e2
173 changed files with 3073 additions and 3118 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -55,7 +55,7 @@ from .openai_utils import (
convert_openai_completion_choice,
convert_openai_completion_stream,
)
from .utils import _is_nvidia_hosted, check_health
from .utils import _is_nvidia_hosted
logger = logging.getLogger(__name__)
@ -134,7 +134,9 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
if content_has_media(content):
raise NotImplementedError("Media is not supported")
await check_health(self._config) # this raises errors
# ToDo: check health of NeMo endpoints and enable this
# removing this health check as NeMo customizer endpoint health check is returning 404
# await check_health(self._config) # this raises errors
provider_model_id = self.get_provider_model_id(model_id)
request = convert_completion_request(
@ -203,7 +205,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
extra_body["input_type"] = task_type_options[task_type]
try:
response = await self._client.embeddings.create(
response = await self._get_client(model).embeddings.create(
model=model,
input=input,
extra_body=extra_body,
@ -236,7 +238,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
if tool_prompt_format:
warnings.warn("tool_prompt_format is not supported by NVIDIA NIM, ignoring", stacklevel=2)
await check_health(self._config) # this raises errors
# await check_health(self._config) # this raises errors
provider_model_id = self.get_provider_model_id(model_id)
request = await convert_chat_completion_request(