From 06bebcb65f2b2826d94f47ca0c2b36ea0ea80c67 Mon Sep 17 00:00:00 2001 From: Wing Lian Date: Tue, 2 Sep 2025 13:13:23 -0400 Subject: [PATCH] run cu128-2.8.0 e2e tests on B200 (#3126) * run cu128-2.8.0 e2e tests on B200 * not an int :facepalm: * fix yaml --- .github/workflows/tests.yml | 2 ++ cicd/single_gpu.py | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index 59011ee77..337230d4a 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -303,6 +303,7 @@ jobs: python_version: "3.11" pytorch: 2.8.0 num_gpus: 1 + gpu_type: "B200" axolotl_extras: steps: - name: Checkout @@ -324,6 +325,7 @@ jobs: echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV + echo "GPU_TYPE=${{ matrix.gpu_type || 'L40S'}}" >> $GITHUB_ENV echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV - name: Run tests job on Modal diff --git a/cicd/single_gpu.py b/cicd/single_gpu.py index 0e2922e90..5a06a34f0 100644 --- a/cicd/single_gpu.py +++ b/cicd/single_gpu.py @@ -57,7 +57,8 @@ VOLUME_CONFIG = { } N_GPUS = int(os.environ.get("N_GPUS", 1)) -GPU_CONFIG = f"L40S:{N_GPUS}" +GPU_TYPE = os.environ.get("GPU_TYPE", "L40S") +GPU_CONFIG = f"{GPU_TYPE}:{N_GPUS}" def run_cmd(cmd: str, run_folder: str):