phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 13:14:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove dead code (#3729)

Browse source 
# What does this PR do?
Removing some dead code, found by vulture and checked by claude that
there are no references or imports for these


## Test Plan
CI
This commit is contained in:
slekkala1 2025-10-07 20:26:02 -07:00 • committed by GitHub
parent b6e9f41041
commit 1ac320b7e6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 8 additions and 359 deletions
Download patch file Download diff file Expand all files Collapse all files

45
llama_stack/providers/remote/inference/nvidia/utils.py
View file

@ -4,53 +4,8 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import httpx
from llama_stack.log import get_logger
from . import NVIDIAConfig
logger = get_logger(name=__name__, category="inference::nvidia")
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
Args:
url (str): URL of the server
Returns:
Tuple[bool, bool]: (is_live, is_ready)
"""
async with httpx.AsyncClient() as client:
live = await client.get(f"{url}/v1/health/live")
ready = await client.get(f"{url}/v1/health/ready")
return live.status_code == 200, ready.status_code == 200
async def check_health(config: NVIDIAConfig) -> None:
"""
Check if the server is running and ready
Args:
url (str): URL of the server
Raises:
RuntimeError: If the server is not running or ready
"""
if not _is_nvidia_hosted(config):
logger.info("Checking NVIDIA NIM health...")
try:
is_live, is_ready = await _get_health(config.url)
if not is_live:
raise ConnectionError("NVIDIA NIM is not running")
if not is_ready:
raise ConnectionError("NVIDIA NIM is not ready")
# TODO(mf): should we wait for the server to be ready?
except httpx.ConnectError as e:
raise ConnectionError(f"Failed to connect to NVIDIA NIM: {e}") from e