Skip to content

testing: track the llama export times #15535

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 5 commits into
base: main
Choose a base branch
from
Draft

testing: track the llama export times #15535

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b9b901c
debug: add some timestamping to see how the timing would be called
Nov 3, 2025
6281f1d
Merge branch 'main' into dev/issue_10761
mroreo Nov 3, 2025
dd14b0e
Merge branch 'main' into dev/issue_10761
mroreo Nov 3, 2025
943e15b
fix: add a max export time arg with a default of 500
Nov 4, 2025
4fb6946
fix: add a comment for legibility
Nov 4, 2025
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
22 changes: 22 additions & 0 deletions .ci/scripts/test_llama.sh
100644 → 100755
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,9 @@ PT2E_QUANTIZE="${PT2E_QUANTIZE:-}"
# Default CMake Build Type to release mode
CMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE:-Release}

# Default maximum export time.
MAX_EXPORT_TIME=${MAX_EXPORT_TIME:500}

# Argument validation is done individually below for each required parameter
if [[ -z "${MODEL_NAME:-}" ]]; then
echo "Missing model name, exiting..."
Expand Down Expand Up @@ -255,9 +258,28 @@ fi
if [[ "${QUANTIZE_KV_CACHE}" == "ON" ]]; then
EXPORT_ARGS="${EXPORT_ARGS} model.quantize_kv_cache=true"
fi

# Display the time
echo "Starting model export at $(date +"%Y-%m-%d %H:%M:%S")"
echo "Configuration: MODE=${MODE}, DTYPE=${DTYPE}, MODEL=${MODEL_NAME}"
EXPORT_START_TIME=$(date +%s)

# Add dynamically linked library location
$PYTHON_EXECUTABLE -m extension.llm.export.export_llm ${EXPORT_ARGS}

EXPORT_END_TIME=$(date +%s)
EXPORT_DURATION=$((EXPORT_END_TIME - EXPORT_START_TIME))
echo "Model export completed at $(date +"%Y-%m-%d %H:%M:%S") - Duration: ${EXPORT_DURATION} seconds"

# Check export time against threshold. Default is 500 seconds.
if [ $EXPORT_DURATION -gt $MAX_EXPORT_TIME ]; then
echo "Failure; Export took ${EXPORT_DURATION} seconds, exceeding threshold of ${MAX_EXPORT_TIME} seconds"
exit 1
fi

echo "Successl Export time check passed: ${EXPORT_DURATION}s <= ${MAX_EXPORT_TIME}s"


# Create tokenizer.bin.
echo "Creating tokenizer.bin"
$PYTHON_EXECUTABLE -m pytorch_tokenizers.tools.llama2c.convert -t tokenizer.model -o tokenizer.bin
Expand Down