phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 20:39:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add test cases

Browse source
This commit is contained in:
Ubuntu 2025-03-08 11:43:13 +00:00
parent 0db524cc26
commit d8a5455fe0
5 changed files with 425 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -52,7 +52,7 @@ 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__)
@ -99,7 +99,9 @@ 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
request = convert_completion_request(
request=CompletionRequest(
@ -179,7 +181,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
if tool_prompt_format:
warnings.warn("tool_prompt_format is not supported by NVIDIA NIM, ignoring")
await check_health(self._config) # this raises errors
# await check_health(self._config) # this raises errors
request = await convert_chat_completion_request(
request=ChatCompletionRequest(