Skip to content

add parakeet into cuda benckmark ci #17182

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

Merged
meta-codesync merged 4 commits into from
Feb 8, 2026
+34 −1
Merged

add parakeet into cuda benckmark ci #17182

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
25cba56
add parakeet into cuda benckmark ci
Gasoonjia Feb 3, 2026
d343d49
Update on "add parakeet into cuda benckmark ci"
Gasoonjia Feb 4, 2026
718ef6f
Update on "add parakeet into cuda benckmark ci"
Gasoonjia Feb 6, 2026
443bcc2
Update on "add parakeet into cuda benckmark ci"
Gasoonjia Feb 7, 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
15 changes: 14 additions & 1 deletion .github/workflows/cuda-perf.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ jobs:
shell: bash
env:
# All available models and quantizations
ALL_MODELS: 'mistralai/Voxtral-Mini-3B-2507,openai/whisper-small,openai/whisper-medium,openai/whisper-large-v3-turbo,google/gemma-3-4b-it'
ALL_MODELS: 'mistralai/Voxtral-Mini-3B-2507,openai/whisper-small,openai/whisper-medium,openai/whisper-large-v3-turbo,google/gemma-3-4b-it,nvidia/parakeet-tdt'
ALL_QUANTIZATIONS: 'non-quantized,quantized-int4-tile-packed,quantized-int4-weight-only'
NUM_RUNS: ${{ inputs.num_runs || '50' }}
RUN_ALL_MODELS: ${{ inputs.run_all_models || 'false' }}
Expand Down Expand Up @@ -234,6 +234,12 @@ jobs:
if [ -f "${RUNNER_ARTIFACT_DIR}/output.wav" ]; then
cp "${RUNNER_ARTIFACT_DIR}/output.wav" model_artifacts/
fi
if [ -f "${RUNNER_ARTIFACT_DIR}/tokenizer.model" ]; then
cp "${RUNNER_ARTIFACT_DIR}/tokenizer.model" model_artifacts/
fi
if [ -f "${RUNNER_ARTIFACT_DIR}/test_audio.wav" ]; then
cp "${RUNNER_ARTIFACT_DIR}/test_audio.wav" model_artifacts/
fi
# Copy tokenizer files
for file in tokenizer.json tokenizer_config.json special_tokens_map.json; do
if [ -f "${RUNNER_ARTIFACT_DIR}/$file" ]; then
Expand Down Expand Up @@ -286,6 +292,13 @@ jobs:
RUNNER_CMD="$RUNNER --model_path model_artifacts/model.pte --data_path model_artifacts/aoti_cuda_blob.ptd --tokenizer_path model_artifacts/ --image_path $IMAGE --temperature 0"
MODEL_NAME="gemma3_${{ matrix.quant }}"
;;
nvidia/parakeet-tdt)
RUNNER="cmake-out/examples/models/parakeet/parakeet_runner"
AUDIO="model_artifacts/test_audio.wav"
TOKENIZER="model_artifacts/tokenizer.model"
RUNNER_CMD="$RUNNER --model_path model_artifacts/model.pte --data_path model_artifacts/aoti_cuda_blob.ptd --audio_path $AUDIO --tokenizer_path $TOKENIZER"
MODEL_NAME="parakeet_${{ matrix.quant }}"
;;
*)
echo "Error: Unsupported model '${{ matrix.model }}'"
exit 1
Expand Down
Loading