phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 18:12:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

move is_hosted out of the NVIDIAConfig api

Browse source
This commit is contained in:
Matthew Farrellee 2024-11-21 15:08:31 -05:00
parent 988741c276
commit 8944491c3c
3 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -11,6 +11,10 @@ import httpx
from ._config import NVIDIAConfig
def _is_nvidia_hosted(config: NVIDIAConfig) -> bool:
return "integrate.api.nvidia.com" in config.url
async def _get_health(url: str) -> Tuple[bool, bool]:
"""
Query {url}/v1/health/{live,ready} to check if the server is running and ready
@ -37,7 +41,7 @@ async def check_health(config: NVIDIAConfig) -> None:
Raises:
RuntimeError: If the server is not running or ready
"""
if not config.is_hosted:
if not _is_nvidia_hosted(config):
print("Checking NVIDIA NIM health...")
try:
is_live, is_ready = await _get_health(config.url)