Skip to content

refactor: replace tf model with onnx model for L0_response_cache #8114

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

refactor: replace tf model with onnx model for L0_response_cache #8114

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions qa/L0_response_cache/ensemble_cache_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#!/usr/bin/env python3
# Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright 2024-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
Expand Down Expand Up @@ -48,8 +48,8 @@ def setUp(self):
self.triton_client = grpcclient.InferenceServerClient(
"localhost:8001", verbose=True
)
self.ensemble_model = "simple_graphdef_float32_float32_float32"
self.composing_model = "graphdef_float32_float32_float32"
self.ensemble_model = "simple_onnx_float32_float32_float32"
self.composing_model = "onnx_float32_float32_float32"
self.model_directory = os.path.join(os.getcwd(), "models", "ensemble_models")
self.ensemble_config_file = os.path.join(
self.model_directory, self.ensemble_model, "config.pbtxt"
Expand Down Expand Up @@ -125,7 +125,7 @@ def _run_inference_and_validate(self, model):
Helper function that takes model as a parameter to verify the corresponding model's stats
The passed model is composing model for test case `test_ensemble_composing_model_cache_enabled`
For other testcases, the top-level ensemble model stats are verified.
* loads the simple_graphdef_float32_float32_float32 and graphdef_float32_float32_float32
* loads the simple_onnx_float32_float32_float32 and onnx_float32_float32_float32
and verifies if they are loaded properly.
* Checks the initial statistics of the model passed in the parameter
Expected - baseline statistics to be all empty metrics since
Expand Down
6 changes: 3 additions & 3 deletions qa/L0_response_cache/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#!/bin/bash
# Copyright 2022-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright 2022-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
Expand Down Expand Up @@ -64,8 +64,8 @@ ENSEMBLE_CACHE_COMPOSING_DECOUPLED="${MODEL_DIR}/ensemble_cache_composing_decoup
rm -fr ${ENSEMBLE_MODEL_DIR} && mkdir ${ENSEMBLE_MODEL_DIR}
rm -fr ${ENSEMBLE_CACHE_DECOUPLED} && mkdir ${ENSEMBLE_CACHE_DECOUPLED}
rm -fr ${ENSEMBLE_CACHE_COMPOSING_DECOUPLED} && mkdir ${ENSEMBLE_CACHE_COMPOSING_DECOUPLED}
ENSEMBLE_MODEL="simple_graphdef_float32_float32_float32"
COMPOSING_MODEL="graphdef_float32_float32_float32"
ENSEMBLE_MODEL="simple_onnx_float32_float32_float32"
COMPOSING_MODEL="onnx_float32_float32_float32"

cp -r "/data/inferenceserver/${REPO_VERSION}/qa_ensemble_model_repository/qa_model_repository/${ENSEMBLE_MODEL}" "${ENSEMBLE_MODEL_DIR}/${ENSEMBLE_MODEL}"
cp -r "/data/inferenceserver/${REPO_VERSION}/qa_model_repository/${COMPOSING_MODEL}" "${ENSEMBLE_MODEL_DIR}/${COMPOSING_MODEL}"
Expand Down
Loading