Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
66 lines
2.5 KiB
YAML
66 lines
2.5 KiB
YAML
name: Self-hosted runner (benchmark)
|
|
|
|
on:
|
|
push:
|
|
branches: [main]
|
|
pull_request:
|
|
types: [ opened, labeled, reopened, synchronize ]
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
|
|
cancel-in-progress: true
|
|
|
|
env:
|
|
HF_HOME: /mnt/cache
|
|
DATASET_ID: hf-benchmarks/transformers
|
|
MODEL_ID: meta-llama/Llama-3.1-8B-Instruct
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
jobs:
|
|
benchmark:
|
|
name: Benchmark
|
|
strategy:
|
|
matrix:
|
|
# group: [aws-g5-4xlarge-cache, aws-p4d-24xlarge-plus] (A100 runner is not enabled)
|
|
group: [aws-g5-4xlarge-cache]
|
|
runs-on:
|
|
group: ${{ matrix.group }}
|
|
if: |
|
|
(github.event_name == 'pull_request' && contains( github.event.pull_request.labels.*.name, 'run-benchmark') )||
|
|
(github.event_name == 'push' && github.ref == 'refs/heads/main')
|
|
container:
|
|
image: huggingface/transformers-all-latest-gpu
|
|
options: --gpus all --privileged --ipc host
|
|
steps:
|
|
- name: Get repo
|
|
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
|
with:
|
|
fetch-depth: 1
|
|
persist-credentials: false
|
|
|
|
- name: Install benchmark script dependencies
|
|
run: python3 -m pip install -r benchmark_v2/requirements.txt kernels
|
|
|
|
- name: Reinstall transformers in edit mode (remove the one installed during docker image build)
|
|
run: python3 -m pip uninstall -y transformers && python3 -m pip install -e ".[torch]"
|
|
|
|
- name: Run benchmark
|
|
run: |
|
|
git config --global --add safe.directory /__w/transformers/transformers
|
|
if [ "$GITHUB_EVENT_NAME" = "pull_request" ]; then
|
|
commit_id=$(echo "${{ github.event.pull_request.head.sha }}")
|
|
elif [ "$GITHUB_EVENT_NAME" = "push" ]; then
|
|
commit_id=$GITHUB_SHA
|
|
fi
|
|
commit_msg=$(git show -s --format=%s | cut -c1-70)
|
|
python3 benchmark_v2/run_benchmarks.py -b 32 -s 128 -n 256 --level 2 --branch-name "$BRANCH_NAME" --commit-id "$commit_id" --commit-message "$commit_msg" --model-id "$MODEL_ID" --log-level INFO --push-result-to-dataset "$DATASET_ID"
|
|
env:
|
|
HF_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
|
|
PUSH_TO_HUB_TOKEN: ${{ secrets.PUSH_TO_HUB_TOKEN }}
|
|
# Enable this to see debug logs
|
|
# HF_HUB_VERBOSITY: debug
|
|
# TRANSFORMERS_VERBOSITY: debug
|
|
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
|