mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
4e6c984c26
# What does this PR do? this PR adds a basic inference adapter to NVIDIA NIMs what it does - - chat completion api - tool calls - streaming - structured output - logprobs - support hosted NIM on integrate.api.nvidia.com - support downloaded NIM containers what it does not do - - completion api - embedding api - vision models - builtin tools - have certainty that sampling strategies are correct ## Feature/Issue validation/testing/test plan `pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_API_KEY=...` all tests should pass. there are pydantic v1 warnings. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [x] Did you write any new necessary tests? Thanks for contributing 🎉!
54 lines
1.6 KiB
Python
54 lines
1.6 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.
|
|
|
|
from typing import Tuple
|
|
|
|
import httpx
|
|
|
|
from . 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
|
|
|
|
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):
|
|
print("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
|