[sharktank] Update block_seq_stride for perplexity CI tests #1257
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Copyright 2024 Advanced Micro Devices, Inc. | |
# | |
# Licensed under the Apache License v2.0 with LLVM Exceptions. | |
# See https://llvm.org/LICENSE.txt for license information. | |
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception | |
name: Llama Benchmarking 8B Tests | |
on: | |
workflow_dispatch: | |
pull_request: | |
push: | |
branches: | |
- main | |
concurrency: | |
# A PR number if a pull request and otherwise the commit hash. This cancels | |
# queued and in-progress runs for the same PR (presubmit) or commit | |
# (postsubmit). The workflow name is prepended to avoid conflicts between | |
# different workflows. | |
group: ${{ github.workflow }}-${{ github.event.number || github.sha }} | |
cancel-in-progress: true | |
jobs: | |
test_llama_quick: | |
name: "Llama Benchmarking 8B Tests" | |
strategy: | |
matrix: | |
version: [3.11] | |
fail-fast: false | |
runs-on: llama-mi300x-1 | |
defaults: | |
run: | |
shell: bash | |
env: | |
VENV_DIR: ${{ github.workspace }}/.venv | |
steps: | |
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 | |
- name: Get Current Date | |
id: date | |
run: echo "::set-output name=date::$(date +'%Y-%m-%d')" | |
- name: "Setting up Python" | |
id: setup_python | |
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0 | |
with: | |
python-version: ${{matrix.version}} | |
- name: Create Python venv | |
run: python -m venv ${VENV_DIR} | |
- name: Install pip deps | |
run: | | |
source ${VENV_DIR}/bin/activate | |
python -m pip install --no-compile --upgrade pip | |
# Note: We install in three steps in order to satisfy requirements | |
# from non default locations first. Installing the PyTorch CPU | |
# wheels saves multiple minutes and a lot of bandwidth on runner setup. | |
pip install --no-compile -r pytorch-cpu-requirements.txt | |
# Install nightly IREE packages. | |
# We could also pin to a known working or stable version. | |
pip install -f https://iree.dev/pip-release-links.html --pre --upgrade \ | |
iree-base-compiler \ | |
iree-base-runtime \ | |
iree-turbine | |
pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/ | |
pip freeze | |
- name: Run llama 8b f16 decomposed test | |
run: | | |
source ${VENV_DIR}/bin/activate | |
pytest sharktank/tests/models/llama/benchmark_amdgpu_test.py -v -s --iree-hip-target=gfx942 --iree-device=hip://0 --run-quick-llama-test | |
- name: Upload llama executable files | |
uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4.4.3 | |
with: | |
name: llama-files | |
path: ${{ github.workspace }}/${{ steps.date.outputs.date }} |