Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion .github/actions/cpu-setup/action.yml
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
name: Olive Examples CI | Setup Composite Workflow for CPU runs
name: Olive Recipes CI | Setup Composite Workflow for CPU runs
description: "Composite action to setup environment for CPU workflows"

inputs:
Expand Down
2 changes: 1 addition & 1 deletion .github/actions/cuda-setup/action.yml
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
name: Olive Examples CI | Setup Composite Workflow for CUDA runs
name: Olive Recipes CI | Setup Composite Workflow for CUDA runs
description: "Composite action to setup environment for CUDA workflows"

inputs:
Expand Down
6 changes: 3 additions & 3 deletions .github/scripts/generate_matrix.py
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
os = sys.argv[2]
device = sys.argv[3]

examples = []
recipes = []
for filepath in dirpath.rglob("olive_ci.json"):
with filepath.open() as strm:
for config in json.load(strm):
Expand All @@ -35,8 +35,8 @@
if key not in config:
config[key] = value

examples.append(config)
recipes.append(config)

matrix = {"include": examples}
matrix = {"include": recipes}
output = json.dumps(matrix)
print(output)
8 changes: 4 additions & 4 deletions .github/workflows/main.yml
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
name: main
description: "CI workflow for Olive Examples"
description: "CI workflow for Olive Recipes"

concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
Expand Down Expand Up @@ -59,7 +59,7 @@ jobs:
matrix=$(python .github/scripts/generate_matrix.py . windows cuda)
echo "windows_cuda_matrix=$matrix" >> $GITHUB_OUTPUT

ubuntu-cpu-examples:
ubuntu-cpu-recipes:
needs: generate-matrix
strategy:
fail-fast: false
Expand All @@ -83,7 +83,7 @@ jobs:
working-directory: ${{ github.workspace }}/${{ matrix.cwd }}
run: ${{ matrix.command }}

ubuntu-cuda-examples:
ubuntu-cuda-recipes:
needs: generate-matrix
strategy:
fail-fast: false
Expand All @@ -107,7 +107,7 @@ jobs:
working-directory: ${{ github.workspace }}/${{ matrix.cwd }}
run: ${{ matrix.command }}

windows-cpu-examples:
windows-cpu-recipes:
needs: generate-matrix
strategy:
fail-fast: false
Expand Down
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
<img alt="olive" src="images/olive-black-text.png" height="100" style="max-width: 100%;">
</picture>

## Olive Examples For AI Model Optimization Toolkit Using ONNX Runtime
## Olive Recipes For AI Model Optimization Toolkit Using ONNX Runtime
</div>

This repository compliments [Olive](https://github.com/microsoft/Olive), the AI model optimization toolkit, and includes examples demonstrating its extensive features and use cases. Users of Olive can use these examples as a reference to either optimize publicly available AI models or to optimize their own proprietary models.
This repository compliments [Olive](https://github.com/microsoft/Olive), the AI model optimization toolkit, and includes recipes demonstrating its extensive features and use cases. Users of Olive can use these recipes as a reference to either optimize publicly available AI models or to optimize their own proprietary models.

## Learn more
- [Olive Github Repository](https://github.com/microsoft/Olive)
Expand Down
2 changes: 1 addition & 1 deletion bert/README.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# BERT Optimization
This folder contains examples of BERT optimization using different workflows.
This folder contains recipe for BERT optimization using different workflows.

- QDQ: [Int8 Quantization with QDQ format](#bert-quantization-qdq)
- CPU: [Optimization with PTQ for model from HF/AML](#bert-optimization-with-ptq-on-cpu)
Expand Down
Loading