mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
c3b2b06974
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> This PR renames categories of llama_stack loggers. This PR aligns logging categories as per the package name, as well as reviews from initial https://github.com/meta-llama/llama-stack/pull/2868. This is a follow up to #3061. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Replaces https://github.com/meta-llama/llama-stack/pull/2868 Part of https://github.com/meta-llama/llama-stack/issues/2865 cc @leseb @rhuss Signed-off-by: Mustafa Elbehery <melbeher@redhat.com>
56 lines
1.7 KiB
Python
56 lines
1.7 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# 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
|