From 2fe43376cdde02b7ffcf117e6eb9aa4375fb2dd1 Mon Sep 17 00:00:00 2001 From: ivarflakstad <69173633+ivarflakstad@users.noreply.github.com> Date: Mon, 18 Aug 2025 15:23:27 +0200 Subject: [PATCH] AMD scheduled CI ref env file (#40243) * Reference env-file to be used in docker running the CI * Disable MI300 CI for now --- .../workflows/self-scheduled-amd-mi300-caller.yml | 12 ++++++++---- .../workflows/self-scheduled-amd-mi325-caller.yml | 4 ++++ 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/.github/workflows/self-scheduled-amd-mi300-caller.yml b/.github/workflows/self-scheduled-amd-mi300-caller.yml index d5310fb307..4d2789bcf8 100644 --- a/.github/workflows/self-scheduled-amd-mi300-caller.yml +++ b/.github/workflows/self-scheduled-amd-mi300-caller.yml @@ -5,10 +5,10 @@ name: Self-hosted runner scale set (AMD mi300 scheduled CI caller) # 2gpu scale set: amd-mi300-ci-2gpu on: - workflow_run: - workflows: ["Self-hosted runner (AMD scheduled CI caller)"] - branches: ["main"] - types: [completed] + #workflow_run: + # workflows: ["Self-hosted runner (AMD scheduled CI caller)"] + # branches: ["main"] + # types: [completed] push: branches: - run_amd_scheduled_ci_caller* @@ -24,6 +24,7 @@ jobs: docker: huggingface/transformers-pytorch-amd-gpu ci_event: Scheduled CI (AMD) - mi300 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit torch-pipeline: @@ -36,6 +37,7 @@ jobs: docker: huggingface/transformers-pytorch-amd-gpu ci_event: Scheduled CI (AMD) - mi300 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit example-ci: @@ -48,6 +50,7 @@ jobs: docker: huggingface/transformers-pytorch-amd-gpu ci_event: Scheduled CI (AMD) - mi300 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit deepspeed-ci: @@ -60,4 +63,5 @@ jobs: docker: huggingface/transformers-pytorch-deepspeed-amd-gpu ci_event: Scheduled CI (AMD) - mi300 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit diff --git a/.github/workflows/self-scheduled-amd-mi325-caller.yml b/.github/workflows/self-scheduled-amd-mi325-caller.yml index bc0dfe0e57..8c2bad414b 100644 --- a/.github/workflows/self-scheduled-amd-mi325-caller.yml +++ b/.github/workflows/self-scheduled-amd-mi325-caller.yml @@ -24,6 +24,7 @@ jobs: docker: huggingface/transformers-pytorch-amd-gpu ci_event: Scheduled CI (AMD) - mi325 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit torch-pipeline: @@ -36,6 +37,7 @@ jobs: docker: huggingface/transformers-pytorch-amd-gpu ci_event: Scheduled CI (AMD) - mi325 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit example-ci: @@ -48,6 +50,7 @@ jobs: docker: huggingface/transformers-pytorch-amd-gpu ci_event: Scheduled CI (AMD) - mi325 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit deepspeed-ci: @@ -60,4 +63,5 @@ jobs: docker: huggingface/transformers-pytorch-deepspeed-amd-gpu ci_event: Scheduled CI (AMD) - mi325 report_repo_id: optimum-amd/transformers_daily_ci + env_file: /etc/podinfo/gha-gpu-isolation-settings secrets: inherit