Debug Test #19
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
| name: "Debug Test" | |
| on: | |
| workflow_dispatch: | |
| # pull_request: | |
| # push: | |
| # branches: [multinode-firstclass] | |
| jobs: | |
| get-dsr1-configs: | |
| runs-on: ubuntu-latest | |
| outputs: | |
| multi-node-search-space-config: ${{ steps.get-dsr1-configs.outputs.multi-node-search-space-config }} | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0 | |
| - id: get-dsr1-configs | |
| run: | | |
| pip install pydantic | |
| CONFIG_JSON_MULTI_NODE=$(python3 ${GITHUB_WORKSPACE}/utils/matrix-logic/generate_sweep_configs.py full-sweep --node-type multinode --config-files ${GITHUB_WORKSPACE}/.github/configs/nvidia-master.yaml --seq-lens 1k1k --model-prefix dsr1) | |
| echo "multi-node-search-space-config=$CONFIG_JSON_MULTI_NODE" >> $GITHUB_OUTPUT | |
| echo $CONFIG_JSON_MULTI_NODE | |
| # get-gptoss-configs: | |
| # runs-on: ubuntu-latest | |
| # outputs: | |
| # multi-node-search-space-config: ${{ steps.get-gptoss-configs.outputs.multi-node-search-space-config }} | |
| # steps: | |
| # - name: Checkout code | |
| # uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0 | |
| # - id: get-gptoss-configs | |
| # run: | | |
| # pip install pydantic | |
| # CONFIG_JSON_MULTI_NODE=$(python3 ${GITHUB_WORKSPACE}/utils/matrix-logic/generate_sweep_configs.py full-sweep --node-type multinode --config-files ${GITHUB_WORKSPACE}/.github/configs/nvidia-master.yaml ${GITHUB_WORKSPACE}/.github/configs/amd-master.yaml --seq-lens 1k1k --model-prefix gptoss) | |
| # echo "multi-node-search-space-config=$CONFIG_JSON" >> $GITHUB_OUTPUT | |
| benchmark-dsr1-multi-node: | |
| needs: get-dsr1-configs | |
| uses: ./.github/workflows/benchmark-multinode-tmpl.yml | |
| name: dsr1 1k1k / | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| config: ${{ fromJson(needs.get-dsr1-configs.outputs.multi-node-search-space-config) }} | |
| secrets: inherit | |
| with: | |
| isl: 1024 | |
| osl: 1024 | |
| max-model-len: 2048 | |
| runner: ${{ matrix.config.runner }} | |
| image: ${{ matrix.config.image }} | |
| model: ${{ matrix.config.model }} | |
| framework: ${{ matrix.config.framework }} | |
| precision: ${{ matrix.config.precision }} | |
| exp-name: "dsr1_1k1k" | |
| conc: ${{ matrix.config.conc }} | |
| mtp-mode: ${{ matrix.config.mtp }} | |
| additional-settings: ${{ toJson(matrix.config.additional-settings) }} | |
| prefill-num-worker: ${{ matrix.config.prefill.num-worker }} | |
| prefill-tp: ${{ matrix.config.prefill.tp }} | |
| prefill-ep: ${{ matrix.config.prefill.ep }} | |
| prefill-batch-size: ${{ matrix.config.prefill.batch-size }} | |
| prefill-max-num-tokens: ${{ matrix.config.prefill.max-num-tokens }} | |
| prefill-dp-attn: ${{ matrix.config.prefill.dp-attn }} | |
| decode-num-worker: ${{ matrix.config.decode.num-worker }} | |
| decode-tp: ${{ matrix.config.decode.tp }} | |
| decode-ep: ${{ matrix.config.decode.ep }} | |
| decode-batch-size: ${{ matrix.config.decode.batch-size }} | |
| decode-max-num-tokens: ${{ matrix.config.decode.max-num-tokens }} | |
| decode-dp-attn: ${{ matrix.config.decode.dp-attn }} | |
| # benchmark-gptoss-multi-node: | |
| # needs: get-gptoss-configs | |
| # uses: ./.github/workflows/benchmark-multinode-tmpl.yml | |
| # name: gptoss 1k1k / | |
| # strategy: | |
| # fail-fast: false | |
| # matrix: | |
| # config: ${{ fromJson(needs.get-gptoss-configs.outputs.multi-node-search-space-config) }} | |
| # secrets: inherit | |
| # with: | |
| # exp-name: "gptoss_1k1k" | |
| # isl: 1024 | |
| # osl: 1024 | |
| # max-model-len: 2048 | |
| # runner: ${{ matrix.config.runner }} | |
| # image: ${{ matrix.config.image }} | |
| # model: ${{ matrix.config.model }} | |
| # framework: ${{ matrix.config.framework }} | |
| # precision: ${{ matrix.config.precision }} | |
| # tp: ${{ matrix.config.tp }} | |
| # ep: ${{ matrix.config.ep }} | |
| # dp-attn: ${{ matrix.config.dp-attn }} | |
| # conc: ${{ matrix.config.conc }} | |
| collect-dsr1-results: | |
| needs: benchmark-dsr1-multi-node | |
| if: ${{ always() }} | |
| uses: ./.github/workflows/collect-results.yml | |
| secrets: inherit | |
| with: | |
| exp-name: "dsr1_1k1k" | |
| # collect-gptoss-results: | |
| # needs: benchmark-gptoss-multi-node | |
| # if: ${{ always() }} | |
| # uses: ./.github/workflows/collect-results.yml | |
| # secrets: inherit | |
| # with: | |
| # exp-name: "gptoss_1k1k" | |
| calc-success-rate: | |
| needs: [collect-dsr1-results] | |
| if: ${{ always() }} | |
| runs-on: ubuntu-latest | |
| env: | |
| RESULTS_DIR: "results/" | |
| STATS_FILENAME: "run_stats" | |
| GITHUB_TOKEN: ${{ secrets.REPO_PAT }} | |
| steps: | |
| - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0 | |
| with: | |
| token: ${{ secrets.REPO_PAT }} | |
| fetch-depth: 0 | |
| - name: Download results artifacts | |
| uses: actions/download-artifact@018cc2cf5baa6db3ef3c5f8a56943fffe632ef53 # v6.0.0 | |
| with: | |
| path: ${{ env.RESULTS_DIR }} | |
| pattern: results_* | |
| - name: Install python dependencies | |
| run: pip install PyGithub | |
| - name: Calculate success rate | |
| run: python3 utils/calc_success_rate.py $STATS_FILENAME | |
| - uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5.0.0 | |
| with: | |
| name: "run-stats" | |
| path: ${{ env.STATS_FILENAME }}.json |