From f43762fa7cc5a987be967b0a519ff714e9062841 Mon Sep 17 00:00:00 2001 From: Andy Linfoot <78757007+andy-neuma@users.noreply.github.com> Date: Tue, 9 Jul 2024 16:12:08 -0400 Subject: [PATCH] expand benchmark to h100's (#371) SUMMARY: * updated "build test" to accept an array of benchmarking labels * updated "remote push" and "nightly" workflows to include benchmarking on h100's * adjusted docker job to have same criteria as upload job. did this since upload could fail, but for auth reasons and this shouldn't stop us from push docker. TEST PLAN: runs on remote push --------- Co-authored-by: andy-neuma --- .github/workflows/nm-build-test.yml | 11 +++++++---- .github/workflows/nm-nightly.yml | 2 +- .github/workflows/nm-remote-push.yml | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/.github/workflows/nm-build-test.yml b/.github/workflows/nm-build-test.yml index 1acc2d31717b3..8884bc3dc4a39 100644 --- a/.github/workflows/nm-build-test.yml +++ b/.github/workflows/nm-build-test.yml @@ -58,10 +58,10 @@ on: required: true # benchmark related parameters - benchmark_label: - description: "requested benchmark label (specifies instance)" + benchmark_labels: + description: "stringified Json array of benchmark labels" type: string - default: "" + required: true benchmark_config_list_file: description: "benchmark configs file, e.g. 'nm_benchmark_nightly_configs_list.txt'" type: string @@ -136,9 +136,12 @@ jobs: BENCHMARK: needs: [BUILD] if: success() + strategy: + matrix: + benchmark_label: ${{ fromJson(inputs.benchmark_labels) }} uses: ./.github/workflows/nm-benchmark.yml with: - label: ${{ inputs.benchmark_label }} + label: ${{ matrix.benchmark_label }} benchmark_config_list_file: ${{ inputs.benchmark_config_list_file }} timeout: ${{ inputs.benchmark_timeout }} gitref: ${{ github.ref }} diff --git a/.github/workflows/nm-nightly.yml b/.github/workflows/nm-nightly.yml index 434f2b9032b1b..494198bf496fc 100644 --- a/.github/workflows/nm-nightly.yml +++ b/.github/workflows/nm-nightly.yml @@ -39,7 +39,7 @@ jobs: {"python":"3.11.4","label":"gcp-k8s-l4-solo","test":"neuralmagic/tests/test_skip_env_vars/full.txt"}]' test_timeout: 480 - benchmark_label: gcp-k8s-l4-solo + benchmark_labels: '["gcp-k8s-l4-solo", "k8s-h100-solo"]' benchmark_config_list_file: ./.github/data/nm_benchmark_base_config_list.txt benchmark_timeout: 480 push_benchmark_results_to_gh_pages: "${{ github.event_name == 'schedule' || inputs.push_benchmark_results_to_gh_pages }}" diff --git a/.github/workflows/nm-remote-push.yml b/.github/workflows/nm-remote-push.yml index a44274d9e8a11..17108f345f891 100644 --- a/.github/workflows/nm-remote-push.yml +++ b/.github/workflows/nm-remote-push.yml @@ -25,7 +25,7 @@ jobs: {"python":"3.11.4","label":"gcp-k8s-l4-solo","test":"neuralmagic/tests/test_skip_env_vars/smoke.txt"}]' test_timeout: 480 - benchmark_label: gcp-k8s-l4-solo + benchmark_labels: '["gcp-k8s-l4-solo", "k8s-h100-solo"]' benchmark_config_list_file: ./.github/data/nm_benchmark_base_config_list.txt benchmark_timeout: 480