[tuner] update the calculation of shared memory usage #11076
Workflow file for this run
This file contains hidden or 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: CI - amdsharktank perplexity short | |
| 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_perplexity: | |
| name: "Perplexity tests" | |
| strategy: | |
| matrix: | |
| python-version: [3.11] | |
| torch-version: ["2.6.0"] | |
| runs-on: [linux-mi325-1gpu-ossci-nod-ai] | |
| fail-fast: false | |
| runs-on: ${{matrix.runs-on}} | |
| defaults: | |
| run: | |
| shell: bash | |
| env: | |
| VENV_DIR: ${{ github.workspace }}/.venv | |
| steps: | |
| - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 | |
| - name: "Setting up Python" | |
| id: setup_python | |
| uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0 | |
| with: | |
| python-version: ${{matrix.python-version}} | |
| - name: Create Python venv | |
| run: python -m venv ${VENV_DIR} | |
| - name: Install amdsharktank deps | |
| run: | | |
| source ${VENV_DIR}/bin/activate | |
| amdsharktank/build_tools/install_test_dependencies.sh \ | |
| --torch-version ${{matrix.torch-version}} \ | |
| --pytorch-rocm | |
| pip freeze | |
| - name: Run Perplexity tests | |
| run: | | |
| source ${VENV_DIR}/bin/activate | |
| mkdir perplexity_ci_artifacts | |
| python -m amdsharktank.models.deepseek.toy_deepseek -o "perplexity_ci_artifacts/toy_deepseek.irpa" | |
| pytest \ | |
| -n 8 \ | |
| -v \ | |
| -s \ | |
| amdsharktank/tests/evaluate/ \ | |
| --run-quick-test \ | |
| --bs=4 \ | |
| --device='cuda:0' \ | |
| --iree-device=hip://0 \ | |
| --iree-hip-target=gfx942 \ | |
| --iree-hal-target-device=hip \ | |
| --llama3-8b-f16-model-path=/amdshark-dev/ossci-models/llama_3_1/instruct_8b_fp16.irpa \ | |
| --llama3-8b-f8-model-path=/amdshark-dev/ossci-models/llama_3_1/instruct_8b_fp8_e4m3fnuz.irpa \ | |
| --llama3-8b-tokenizer-path=/amdshark-dev/ossci-models/llama_3_1/tokenizer/tokenizer_config.json \ | |
| --log-cli-level=INFO | |
| ls -lha ${{ github.workspace }}/perplexity_ci_artifacts |