Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
22 commits
Select commit Hold shift + click to select a range
b13594c
[CICD] Add benchmark functional tests for DeepSeek
Mar 11, 2026
da53272
debug0
Mar 11, 2026
8c39f51
debug0
Mar 11, 2026
a1cf7e6
[Benchmark] Enable throughput logging for DeepSeek benchmark test
Mar 11, 2026
55675f0
debug1
Mar 11, 2026
e69bfd6
[Benchmark] Add benchmark functional tests for Aquila and Mixtral
Mar 12, 2026
d9f16ce
[Benchmark] Update gold values for Aquila and Mixtral benchmark tests
Mar 12, 2026
531c293
[Benchmark] Add benchmark functional tests for DeepSeek, Aquila and M…
Mar 12, 2026
ca6016e
[Benchmark] Fix code formatting in check_results.py
Mar 12, 2026
081e905
[Benchmark] Replace Aquila, DeepSeek and Mixtral benchmark tests with…
Mar 12, 2026
431d2f9
Add benchmark data upload step to backend after successful tests
Mar 13, 2026
524c3a6
[Benchmark] Add benchmark output parser and update metrics upload.
Mar 13, 2026
2d9140c
[Benchmark] Update post-benchmark-report action parameters
Mar 16, 2026
4d08333
Fix ruff formatting in parse_benchmark_output.py
Mar 16, 2026
a1b9301
Add jq installation step before benchmark data upload
Mar 16, 2026
8bbbd42
[Benchmark] Support platform/device-classified gold values for benchm…
Mar 17, 2026
0ed04ab
Merge branch 'main' into add-benchmark
zihugithub Mar 18, 2026
50c41ca
Fix pre-commit check issues
Mar 18, 2026
63666b5
Add Megatron-LM installation step to benchmark pipeline
Mar 18, 2026
533a2dc
update parse_benchmark_output.py
Mar 18, 2026
6793520
Update benchmark metrics output to nested object format
Mar 19, 2026
a55157f
Fix pre-commit check issues
Mar 19, 2026
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
54 changes: 40 additions & 14 deletions .github/workflows/all_tests_common.yml
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ jobs:
inference_test_matrix: ${{ steps.config.outputs.inference_test_matrix }}
serve_test_matrix: ${{ steps.config.outputs.serve_test_matrix }}
rl_test_matrix: ${{ steps.config.outputs.rl_test_matrix }}
benchmark_test_matrix: ${{ steps.config.outputs.benchmark_test_matrix }}
pkg_mgr: ${{ steps.config.outputs.pkg_mgr }}
env_path: ${{ steps.config.outputs.env_path }}
env_name_train: ${{ steps.config.outputs.env_name_train }}
Expand Down Expand Up @@ -155,7 +156,6 @@ jobs:
env_name: ${{ needs.checkout_and_config.outputs.env_name_train }}
env_path: ${{ needs.checkout_and_config.outputs.env_path }}

# NOTE: Inference, serve, and rl functional tests are temporarily disabled
functional_tests_inference:
needs:
- checkout_and_config
Expand Down Expand Up @@ -192,6 +192,7 @@ jobs:
env_name: ${{ needs.checkout_and_config.outputs.env_name_serve }}
env_path: ${{ needs.checkout_and_config.outputs.env_path }}

# NOTE: rl functional tests are temporarily disabled
# functional_tests_rl:
# needs:
# - checkout_and_config
Expand All @@ -210,6 +211,24 @@ jobs:
# env_name: ${{ needs.checkout_and_config.outputs.env_name_rl }}
# env_path: ${{ needs.checkout_and_config.outputs.env_path }}

functional_tests_benchmark:
needs:
- checkout_and_config
- unit_tests
if: fromJson(needs.checkout_and_config.outputs.benchmark_test_matrix)[0] != null
uses: ./.github/workflows/functional_tests_benchmark.yml
with:
platform: ${{ inputs.platform }}
test_matrix: ${{ needs.checkout_and_config.outputs.benchmark_test_matrix }}
image: ${{ needs.checkout_and_config.outputs.ci_train_image }}
runs_on: ${{ needs.checkout_and_config.outputs.runs_on }}
container_volumes: ${{ needs.checkout_and_config.outputs.container_volumes }}
container_options: ${{ needs.checkout_and_config.outputs.container_options }}
source_artifact: flagscale-source-${{ github.sha }}
pkg_mgr: ${{ needs.checkout_and_config.outputs.pkg_mgr }}
env_name: ${{ needs.checkout_and_config.outputs.env_name_train }}
env_path: ${{ needs.checkout_and_config.outputs.env_path }}

all_tests_complete:
defaults:
run:
Expand All @@ -219,9 +238,10 @@ jobs:
- unit_tests
- functional_tests_train
- functional_tests_hetero_train
- functional_tests_benchmark
- functional_tests_inference
- functional_tests_serve
# NOTE: Disabled tests removed from needs
# - functional_tests_inference
# - functional_tests_serve
# - functional_tests_rl
runs-on: ubuntu-latest
if: always()
Expand Down Expand Up @@ -249,19 +269,25 @@ jobs:
failed=true
fi

# NOTE: Inference, serve, and rl checks disabled
# if [ "${{ needs.functional_tests_inference.result }}" != "success" ] && \
# [ "${{ needs.functional_tests_inference.result }}" != "skipped" ]; then
# echo "❌ Inference functional tests failed"
# failed=true
# fi
if [ "${{ needs.functional_tests_benchmark.result }}" != "success" ] && \
[ "${{ needs.functional_tests_benchmark.result }}" != "skipped" ]; then
echo "❌ Benchmark tests failed"
failed=true
fi

# if [ "${{ needs.functional_tests_serve.result }}" != "success" ] && \
# [ "${{ needs.functional_tests_serve.result }}" != "skipped" ]; then
# echo "❌ Serve functional tests failed"
# failed=true
# fi
if [ "${{ needs.functional_tests_inference.result }}" != "success" ] && \
[ "${{ needs.functional_tests_inference.result }}" != "skipped" ]; then
echo "❌ Inference functional tests failed"
failed=true
fi

if [ "${{ needs.functional_tests_serve.result }}" != "success" ] && \
[ "${{ needs.functional_tests_serve.result }}" != "skipped" ]; then
echo "❌ Serve functional tests failed"
failed=true
fi

# NOTE: Inference, serve, and rl checks disabled
# if [ "${{ needs.functional_tests_rl.result }}" != "success" ] && \
# [ "${{ needs.functional_tests_rl.result }}" != "skipped" ]; then
# echo "❌ RL functional tests failed"
Expand Down
Loading
Loading