e2e Test - full-sweep --config-files .github/configs/amd-master.yaml --single-node --model-prefix kimik2.5 --runner-type mi300x --seq-len 8k1k #1135
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: End-to-End Tests | |
| run-name: e2e Test - ${{ inputs.test-name || inputs.generate-cli-command || github.event.inputs.generate-cli-command }} | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| generate-cli-command: | |
| description: "Command passed to generate matrix script" | |
| required: true | |
| type: string | |
| test-name: | |
| description: "Name for this test run" | |
| required: false | |
| type: string | |
| ref: | |
| description: "Ref (branch/sha) to checkout for generating configs" | |
| required: false | |
| type: string | |
| workflow_call: | |
| inputs: | |
| generate-cli-command: | |
| description: "Command passed to generate matrix script" | |
| required: true | |
| type: string | |
| test-name: | |
| description: "Name for this test run" | |
| required: false | |
| type: string | |
| ref: | |
| description: "Ref (branch/sha) to checkout for generating configs" | |
| required: false | |
| type: string | |
| jobs: | |
| get-jobs: | |
| runs-on: ubuntu-latest | |
| outputs: | |
| single-node-config: ${{ steps.get-jobs.outputs.single-node-config }} | |
| multi-node-config: ${{ steps.get-jobs.outputs.multi-node-config }} | |
| steps: | |
| - name: Checkout code (ref) | |
| if: ${{ inputs.ref && inputs.ref != '' }} | |
| uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 | |
| with: | |
| ref: ${{ inputs.ref }} | |
| - name: Checkout code (default) | |
| if: ${{ !inputs.ref || inputs.ref == '' }} | |
| uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 | |
| - id: get-jobs | |
| run: | | |
| pip install pydantic | |
| CONFIG_JSON=$(python3 ${GITHUB_WORKSPACE}/utils/matrix_logic/generate_sweep_configs.py \ | |
| ${{ inputs.generate-cli-command || github.event.inputs.generate-cli-command }}) | |
| SINGLE=$(echo "$CONFIG_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps([x for x in d if 'prefill' not in x]))") | |
| MULTI=$(echo "$CONFIG_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps([x for x in d if 'prefill' in x]))") | |
| echo "single-node-config=$SINGLE" >> $GITHUB_OUTPUT | |
| echo "multi-node-config=$MULTI" >> $GITHUB_OUTPUT | |
| test-sweep-multi-node: | |
| needs: get-jobs | |
| if: ${{ needs.get-jobs.outputs.multi-node-config != '[]' }} | |
| uses: ./.github/workflows/benchmark-multinode-tmpl.yml | |
| name: multi-node / | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| config: ${{ fromJson(needs.get-jobs.outputs.multi-node-config) }} | |
| secrets: inherit | |
| with: | |
| isl: ${{ matrix.config.isl }} | |
| osl: ${{ matrix.config.osl }} | |
| max-model-len: ${{ matrix.config.max-model-len }} | |
| runner: ${{ matrix.config.runner }} | |
| image: ${{ matrix.config.image }} | |
| model: ${{ matrix.config.model }} | |
| model-prefix: ${{ matrix.config.model-prefix }} | |
| framework: ${{ matrix.config.framework }} | |
| precision: ${{ matrix.config.precision }} | |
| exp-name: ${{ matrix.config.exp-name }} | |
| conc-list: ${{ toJson(matrix.config.conc) }} | |
| spec-decoding: ${{ matrix.config.spec-decoding }} | |
| disagg: ${{ matrix.config.disagg }} | |
| prefill-num-worker: ${{ matrix.config.prefill.num-worker }} | |
| prefill-tp: ${{ matrix.config.prefill.tp }} | |
| prefill-ep: ${{ matrix.config.prefill.ep }} | |
| prefill-dp-attn: ${{ matrix.config.prefill.dp-attn }} | |
| prefill-additional-settings: ${{ toJson(matrix.config.prefill.additional-settings) }} | |
| decode-num-worker: ${{ matrix.config.decode.num-worker }} | |
| decode-tp: ${{ matrix.config.decode.tp }} | |
| decode-ep: ${{ matrix.config.decode.ep }} | |
| decode-dp-attn: ${{ matrix.config.decode.dp-attn }} | |
| decode-additional-settings: ${{ toJson(matrix.config.decode.additional-settings) }} | |
| ref: ${{ inputs.ref }} | |
| test-sweep-single-node: | |
| needs: get-jobs | |
| if: ${{ needs.get-jobs.outputs.single-node-config != '[]' }} | |
| uses: ./.github/workflows/benchmark-tmpl.yml | |
| name: single-node / | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| config: ${{ fromJson(needs.get-jobs.outputs.single-node-config) }} | |
| secrets: inherit | |
| with: | |
| exp-name: ${{ matrix.config.exp-name }} | |
| isl: ${{ matrix.config.isl }} | |
| osl: ${{ matrix.config.osl }} | |
| max-model-len: ${{ matrix.config.max-model-len }} | |
| runner: ${{ matrix.config.runner }} | |
| image: ${{ matrix.config.image }} | |
| model: ${{ matrix.config.model }} | |
| model-prefix: ${{ matrix.config.model-prefix }} | |
| 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 }} | |
| spec-decoding: ${{ matrix.config.spec-decoding }} | |
| disagg: ${{ matrix.config.disagg }} | |
| run-eval: ${{ matrix.config.run-eval }} | |
| ref: ${{ inputs.ref }} | |
| collect-results: | |
| needs: [test-sweep-multi-node, test-sweep-single-node] | |
| if: ${{ always() }} | |
| uses: ./.github/workflows/collect-results.yml | |
| secrets: inherit | |
| with: | |
| result-prefix: "bmk" | |
| collect-evals: | |
| needs: [test-sweep-multi-node, test-sweep-single-node] | |
| if: ${{ always() }} | |
| uses: ./.github/workflows/collect-evals.yml | |
| secrets: inherit | |
| calc-success-rate: | |
| needs: [collect-results, collect-evals] | |
| if: ${{ always() }} | |
| runs-on: ubuntu-latest | |
| env: | |
| RESULTS_DIR: "results/" | |
| STATS_FILENAME: "run_stats" | |
| GITHUB_TOKEN: ${{ secrets.REPO_PAT }} | |
| steps: | |
| - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 | |
| with: | |
| token: ${{ secrets.REPO_PAT }} | |
| fetch-depth: 0 | |
| - name: Download results artifacts | |
| uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.0 | |
| 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@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0 | |
| with: | |
| name: "run-stats" | |
| path: ${{ env.STATS_FILENAME }}.json |