phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-20 19:56:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: NVIDIA beginner e2e notebook

Browse source
This commit is contained in:
Jash Gulabrai 2025-04-15 23:26:38 -04:00
parent 7cdd2a0410
commit 6927cdf5ce
31 changed files with 888 additions and 1621 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/remote/eval/nvidia/eval.py
View file

@ -14,6 +14,8 @@ from llama_stack.apis.datasets import Datasets
from llama_stack.apis.inference import Inference
from llama_stack.apis.scoring import Scoring, ScoringResult
from llama_stack.providers.datatypes import BenchmarksProtocolPrivate
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from .....apis.common.job_types import Job, JobStatus
from .....apis.eval.eval import BenchmarkConfig, Eval, EvaluateResponse
@ -25,6 +27,7 @@ DEFAULT_NAMESPACE = "nvidia"
class NVIDIAEvalImpl(
Eval,
BenchmarksProtocolPrivate,
ModelRegistryHelper,
):
def __init__(
self,
@ -42,6 +45,8 @@ class NVIDIAEvalImpl(
self.inference_api = inference_api
self.agents_api = agents_api
ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES)
async def initialize(self) -> None: ...
async def shutdown(self) -> None: ...
@ -81,11 +86,13 @@ class NVIDIAEvalImpl(
if benchmark_config.eval_candidate.type == "model"
else benchmark_config.eval_candidate.config.model
)
nvidia_model = self.get_provider_model_id(model)
result = await self._evaluator_post(
"/v1/evaluation/jobs",
{
"config": f"{DEFAULT_NAMESPACE}/{benchmark_id}",
"target": {"type": "model", "model": model},
"target": {"type": "model", "model": nvidia_model},
},
)