From 23ed7ce661cf23df29d3aac3f2c920598c88d1fc Mon Sep 17 00:00:00 2001 From: Mihir Patel Date: Thu, 16 May 2024 13:11:51 -0400 Subject: [PATCH 01/21] add arm --- .github/workflows/docker-configure-build-push.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/docker-configure-build-push.yaml b/.github/workflows/docker-configure-build-push.yaml index 2b6bf4893d..b79dee4ae0 100644 --- a/.github/workflows/docker-configure-build-push.yaml +++ b/.github/workflows/docker-configure-build-push.yaml @@ -87,6 +87,7 @@ jobs: uses: docker/build-push-action@v3 with: context: ${{ inputs.context }} + platforms: linux/amd64,linux/arm64 tags: ${{ env.IMAGE_TAG }} target: ${{ inputs.target }} push: ${{ inputs.push }} From 0f4a0f6edc356a7ba9aceb211d86402f9ad5e8ea Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Thu, 16 May 2024 12:46:59 -0500 Subject: [PATCH 02/21] Update docker-configure-build-push.yaml --- .github/workflows/docker-configure-build-push.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/docker-configure-build-push.yaml b/.github/workflows/docker-configure-build-push.yaml index b79dee4ae0..a1c74940f1 100644 --- a/.github/workflows/docker-configure-build-push.yaml +++ b/.github/workflows/docker-configure-build-push.yaml @@ -36,7 +36,7 @@ on: required: true jobs: configure-build-push: - runs-on: ubuntu-latest + runs-on: mosaic-4wide steps: - name: Maximize Build Space on Worker uses: easimon/maximize-build-space@v4 From e67bc8fc137eef07a6c26ac7893f8a985c5dba4e Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Thu, 16 May 2024 13:55:50 -0500 Subject: [PATCH 03/21] Update build_matrix.yaml --- docker/build_matrix.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index bf743a4ca2..e1eb0713f3 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -236,13 +236,13 @@ TARGET: composer_stage TORCHVISION_VERSION: 0.18.0 - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: ubuntu:20.04 + BASE_IMAGE: ubuntu:22.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 CUDA_VERSION: '' IMAGE_NAME: composer-0-22-0-cpu MOFED_VERSION: 5.5-1.0.3.2 NVIDIA_REQUIRE_CUDA_OVERRIDE: '' - PYTHON_VERSION: '3.11' + PYTHON_VERSION: '3.10' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' PYTORCH_VERSION: 2.3.0 From 46af3fbbeb65ebac314ffe22185eefdf0f0c8155 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Thu, 16 May 2024 14:14:41 -0500 Subject: [PATCH 04/21] Update Dockerfile --- docker/Dockerfile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index c147fe45a7..4744a4afe7 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -271,9 +271,9 @@ ARG MOFED_VERSION RUN if [ -n "$MOFED_VERSION" ] ; then \ mkdir -p /tmp/mofed && \ - wget -nv -P /tmp/mofed http://content.mellanox.com/ofed/MLNX_OFED-${MOFED_VERSION}/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-x86_64.tgz && \ - tar -zxvf /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-x86_64.tgz -C /tmp/mofed && \ - /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-x86_64/mlnxofedinstall --user-space-only --without-fw-update --force && \ + wget -nv -P /tmp/mofed http://content.mellanox.com/ofed/MLNX_OFED-${MOFED_VERSION}/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu22.04-aarch64.tgz && \ + tar -zxvf /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu22.04-aarch64.tgz -C /tmp/mofed && \ + /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu22.04-aarch64/mlnxofedinstall --user-space-only --without-fw-update --force && \ rm -rf /tmp/mofed ; \ fi From 7ac17f31f22b7d35106bfc980bd6821eb1213f86 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Thu, 16 May 2024 14:30:33 -0500 Subject: [PATCH 05/21] Update build_matrix.yaml --- docker/build_matrix.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index e1eb0713f3..866e548690 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -240,7 +240,7 @@ COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 CUDA_VERSION: '' IMAGE_NAME: composer-0-22-0-cpu - MOFED_VERSION: 5.5-1.0.3.2 + MOFED_VERSION: 5.6-2.0.9.0 NVIDIA_REQUIRE_CUDA_OVERRIDE: '' PYTHON_VERSION: '3.10' PYTORCH_NIGHTLY_URL: '' From ebcdba7688201ea3da6ee985c366df2d0e79c5ac Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Thu, 16 May 2024 14:38:42 -0500 Subject: [PATCH 06/21] Update build_matrix.yaml --- docker/build_matrix.yaml | 472 +++++++++++++++++++-------------------- 1 file changed, 236 insertions(+), 236 deletions(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index 866e548690..a7c7886ebf 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -1,240 +1,240 @@ # This file is automatically generated by generate_build_matrix.py. DO NOT EDIT! -- AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.1 - IMAGE_NAME: torch-2-3-0-cu121 - MOFED_VERSION: 5.5-1.0.3.2 - NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 - brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 - brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 - brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 - brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 - brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 - brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 - brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 - brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 - brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 - brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 - brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 - brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 - brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 - PYTHON_VERSION: '3.11' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.3.0 - TAGS: - - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04 - - mosaicml/pytorch:latest - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.18.0 -- AWS_OFI_NCCL_VERSION: v1.9.1-aws - BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.1 - IMAGE_NAME: torch-2-3-0-cu121-aws - MOFED_VERSION: '' - NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 - brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 - brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 - brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 - brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 - brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 - brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 - brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 - brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 - brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 - brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 - brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 - brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 - brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 - PYTHON_VERSION: '3.11' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.3.0 - TAGS: - - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04-aws - - mosaicml/pytorch:latest-aws - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.18.0 -- AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: ubuntu:20.04 - CUDA_VERSION: '' - IMAGE_NAME: torch-2-3-0-cpu - MOFED_VERSION: '' - NVIDIA_REQUIRE_CUDA_OVERRIDE: '' - PYTHON_VERSION: '3.11' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.3.0 - TAGS: - - mosaicml/pytorch:2.3.0_cpu-python3.11-ubuntu20.04 - - mosaicml/pytorch:latest_cpu - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.18.0 -- AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.1 - IMAGE_NAME: torch-2-2-2-cu121 - MOFED_VERSION: 5.5-1.0.3.2 - NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 - brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 - brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 - brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 - brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 - brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 - brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 - brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 - brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 - brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 - brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 - brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 - brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 - brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 - PYTHON_VERSION: '3.11' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.2.2 - TAGS: - - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04 - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.17.2 -- AWS_OFI_NCCL_VERSION: v1.9.1-aws - BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.1 - IMAGE_NAME: torch-2-2-2-cu121-aws - MOFED_VERSION: '' - NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 - brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 - brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 - brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 - brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 - brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 - brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 - brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 - brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 - brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 - brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 - brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 - brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 - brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 - PYTHON_VERSION: '3.11' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.2.2 - TAGS: - - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04-aws - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.17.2 -- AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: ubuntu:20.04 - CUDA_VERSION: '' - IMAGE_NAME: torch-2-2-2-cpu - MOFED_VERSION: '' - NVIDIA_REQUIRE_CUDA_OVERRIDE: '' - PYTHON_VERSION: '3.11' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.2.2 - TAGS: - - mosaicml/pytorch:2.2.2_cpu-python3.11-ubuntu20.04 - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.17.2 -- AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.1 - IMAGE_NAME: torch-2-1-2-cu121 - MOFED_VERSION: 5.5-1.0.3.2 - NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 - brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 - brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 - brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 - brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 - brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 - brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 - brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 - brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 - brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 - brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 - brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 - brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 - brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 - PYTHON_VERSION: '3.10' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.1.2 - TAGS: - - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04 - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.16.2 -- AWS_OFI_NCCL_VERSION: v1.9.1-aws - BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.1 - IMAGE_NAME: torch-2-1-2-cu121-aws - MOFED_VERSION: '' - NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 - brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 - brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 - brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 - brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 - brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 - brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 - brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 - brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 - brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 - brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 - brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 - brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 - brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 - PYTHON_VERSION: '3.10' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.1.2 - TAGS: - - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04-aws - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.16.2 -- AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: ubuntu:20.04 - CUDA_VERSION: '' - IMAGE_NAME: torch-2-1-2-cpu - MOFED_VERSION: '' - NVIDIA_REQUIRE_CUDA_OVERRIDE: '' - PYTHON_VERSION: '3.10' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.1.2 - TAGS: - - mosaicml/pytorch:2.1.2_cpu-python3.10-ubuntu20.04 - TARGET: pytorch_stage - TORCHVISION_VERSION: 0.16.2 -- AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 - COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 - CUDA_VERSION: 12.1.1 - IMAGE_NAME: composer-0-22-0 - MOFED_VERSION: 5.5-1.0.3.2 - NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 - brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 - brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 - brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 - brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 - brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 - brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 - brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 - brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 - brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 - brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 - brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 - brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 - brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 - PYTHON_VERSION: '3.11' - PYTORCH_NIGHTLY_URL: '' - PYTORCH_NIGHTLY_VERSION: '' - PYTORCH_VERSION: 2.3.0 - TAGS: - - mosaicml/composer:0.22.0 - - mosaicml/composer:latest - TARGET: composer_stage - TORCHVISION_VERSION: 0.18.0 +# - AWS_OFI_NCCL_VERSION: '' +# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 +# CUDA_VERSION: 12.1.1 +# IMAGE_NAME: torch-2-3-0-cu121 +# MOFED_VERSION: 5.5-1.0.3.2 +# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 +# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 +# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 +# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 +# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 +# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 +# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 +# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 +# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 +# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 +# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 +# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 +# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 +# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 +# PYTHON_VERSION: '3.11' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.3.0 +# TAGS: +# - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04 +# - mosaicml/pytorch:latest +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.18.0 +# - AWS_OFI_NCCL_VERSION: v1.9.1-aws +# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 +# CUDA_VERSION: 12.1.1 +# IMAGE_NAME: torch-2-3-0-cu121-aws +# MOFED_VERSION: '' +# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 +# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 +# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 +# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 +# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 +# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 +# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 +# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 +# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 +# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 +# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 +# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 +# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 +# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 +# PYTHON_VERSION: '3.11' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.3.0 +# TAGS: +# - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04-aws +# - mosaicml/pytorch:latest-aws +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.18.0 +# - AWS_OFI_NCCL_VERSION: '' +# BASE_IMAGE: ubuntu:20.04 +# CUDA_VERSION: '' +# IMAGE_NAME: torch-2-3-0-cpu +# MOFED_VERSION: '' +# NVIDIA_REQUIRE_CUDA_OVERRIDE: '' +# PYTHON_VERSION: '3.11' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.3.0 +# TAGS: +# - mosaicml/pytorch:2.3.0_cpu-python3.11-ubuntu20.04 +# - mosaicml/pytorch:latest_cpu +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.18.0 +# - AWS_OFI_NCCL_VERSION: '' +# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 +# CUDA_VERSION: 12.1.1 +# IMAGE_NAME: torch-2-2-2-cu121 +# MOFED_VERSION: 5.5-1.0.3.2 +# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 +# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 +# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 +# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 +# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 +# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 +# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 +# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 +# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 +# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 +# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 +# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 +# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 +# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 +# PYTHON_VERSION: '3.11' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.2.2 +# TAGS: +# - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04 +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.17.2 +# - AWS_OFI_NCCL_VERSION: v1.9.1-aws +# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 +# CUDA_VERSION: 12.1.1 +# IMAGE_NAME: torch-2-2-2-cu121-aws +# MOFED_VERSION: '' +# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 +# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 +# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 +# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 +# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 +# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 +# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 +# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 +# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 +# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 +# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 +# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 +# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 +# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 +# PYTHON_VERSION: '3.11' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.2.2 +# TAGS: +# - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04-aws +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.17.2 +# - AWS_OFI_NCCL_VERSION: '' +# BASE_IMAGE: ubuntu:20.04 +# CUDA_VERSION: '' +# IMAGE_NAME: torch-2-2-2-cpu +# MOFED_VERSION: '' +# NVIDIA_REQUIRE_CUDA_OVERRIDE: '' +# PYTHON_VERSION: '3.11' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.2.2 +# TAGS: +# - mosaicml/pytorch:2.2.2_cpu-python3.11-ubuntu20.04 +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.17.2 +# - AWS_OFI_NCCL_VERSION: '' +# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 +# CUDA_VERSION: 12.1.1 +# IMAGE_NAME: torch-2-1-2-cu121 +# MOFED_VERSION: 5.5-1.0.3.2 +# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 +# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 +# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 +# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 +# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 +# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 +# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 +# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 +# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 +# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 +# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 +# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 +# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 +# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 +# PYTHON_VERSION: '3.10' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.1.2 +# TAGS: +# - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04 +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.16.2 +# - AWS_OFI_NCCL_VERSION: v1.9.1-aws +# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 +# CUDA_VERSION: 12.1.1 +# IMAGE_NAME: torch-2-1-2-cu121-aws +# MOFED_VERSION: '' +# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 +# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 +# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 +# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 +# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 +# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 +# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 +# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 +# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 +# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 +# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 +# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 +# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 +# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 +# PYTHON_VERSION: '3.10' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.1.2 +# TAGS: +# - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04-aws +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.16.2 +# - AWS_OFI_NCCL_VERSION: '' +# BASE_IMAGE: ubuntu:20.04 +# CUDA_VERSION: '' +# IMAGE_NAME: torch-2-1-2-cpu +# MOFED_VERSION: '' +# NVIDIA_REQUIRE_CUDA_OVERRIDE: '' +# PYTHON_VERSION: '3.10' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.1.2 +# TAGS: +# - mosaicml/pytorch:2.1.2_cpu-python3.10-ubuntu20.04 +# TARGET: pytorch_stage +# TORCHVISION_VERSION: 0.16.2 +# - AWS_OFI_NCCL_VERSION: '' +# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 +# COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 +# CUDA_VERSION: 12.1.1 +# IMAGE_NAME: composer-0-22-0 +# MOFED_VERSION: 5.5-1.0.3.2 +# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 +# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 +# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 +# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 +# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 +# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 +# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 +# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 +# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 +# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 +# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 +# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 +# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 +# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 +# PYTHON_VERSION: '3.11' +# PYTORCH_NIGHTLY_URL: '' +# PYTORCH_NIGHTLY_VERSION: '' +# PYTORCH_VERSION: 2.3.0 +# TAGS: +# - mosaicml/composer:0.22.0 +# - mosaicml/composer:latest +# TARGET: composer_stage +# TORCHVISION_VERSION: 0.18.0 - AWS_OFI_NCCL_VERSION: '' BASE_IMAGE: ubuntu:22.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 From bc69f9f3988b44fd4625fe448255181ff8f02ef9 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Thu, 16 May 2024 14:51:49 -0500 Subject: [PATCH 07/21] Update docker-configure-build-push.yaml --- .github/workflows/docker-configure-build-push.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/docker-configure-build-push.yaml b/.github/workflows/docker-configure-build-push.yaml index a1c74940f1..61993a435a 100644 --- a/.github/workflows/docker-configure-build-push.yaml +++ b/.github/workflows/docker-configure-build-push.yaml @@ -87,7 +87,7 @@ jobs: uses: docker/build-push-action@v3 with: context: ${{ inputs.context }} - platforms: linux/amd64,linux/arm64 + platforms: linux/arm64 tags: ${{ env.IMAGE_TAG }} target: ${{ inputs.target }} push: ${{ inputs.push }} From 04fecc05450e8d7e70d713ea1eeea40d3b32d447 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Thu, 16 May 2024 15:13:55 -0500 Subject: [PATCH 08/21] Update build_matrix.yaml --- docker/build_matrix.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index a7c7886ebf..967b2ca3cd 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -236,7 +236,7 @@ # TARGET: composer_stage # TORCHVISION_VERSION: 0.18.0 - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: ubuntu:22.04 + BASE_IMAGE: arm64v8/ubuntu:22.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 CUDA_VERSION: '' IMAGE_NAME: composer-0-22-0-cpu From ccfe107a69b8c6e04376e0ebb537237bdaee25f1 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 15:38:11 -0500 Subject: [PATCH 09/21] PIL 9.0.0 compatible with 20.04 --- docker/Dockerfile | 4 ++-- docker/build_matrix.yaml | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index 4744a4afe7..a9c5cd3b4d 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -272,8 +272,8 @@ ARG MOFED_VERSION RUN if [ -n "$MOFED_VERSION" ] ; then \ mkdir -p /tmp/mofed && \ wget -nv -P /tmp/mofed http://content.mellanox.com/ofed/MLNX_OFED-${MOFED_VERSION}/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu22.04-aarch64.tgz && \ - tar -zxvf /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu22.04-aarch64.tgz -C /tmp/mofed && \ - /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu22.04-aarch64/mlnxofedinstall --user-space-only --without-fw-update --force && \ + tar -zxvf /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-aarch64.tgz -C /tmp/mofed && \ + /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-aarch64/mlnxofedinstall --user-space-only --without-fw-update --force && \ rm -rf /tmp/mofed ; \ fi diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index 967b2ca3cd..736b96b06a 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -236,11 +236,11 @@ # TARGET: composer_stage # TORCHVISION_VERSION: 0.18.0 - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: arm64v8/ubuntu:22.04 + BASE_IMAGE: arm64v8/ubuntu:20.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 CUDA_VERSION: '' IMAGE_NAME: composer-0-22-0-cpu - MOFED_VERSION: 5.6-2.0.9.0 + MOFED_VERSION: 5.5-1.0.3.2 NVIDIA_REQUIRE_CUDA_OVERRIDE: '' PYTHON_VERSION: '3.10' PYTORCH_NIGHTLY_URL: '' From 311ff8a35024ae9c31d8c60c8e99c59888360a6d Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 15:39:07 -0500 Subject: [PATCH 10/21] 3.8 --- docker/build_matrix.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index 736b96b06a..2b717ab383 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -242,7 +242,7 @@ IMAGE_NAME: composer-0-22-0-cpu MOFED_VERSION: 5.5-1.0.3.2 NVIDIA_REQUIRE_CUDA_OVERRIDE: '' - PYTHON_VERSION: '3.10' + PYTHON_VERSION: '3.8' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' PYTORCH_VERSION: 2.3.0 From a8acb814a065eb1b5f6d41ff05fa635d4344baec Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 16:11:50 -0500 Subject: [PATCH 11/21] SIMD only compat with x86 --- docker/Dockerfile | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index a9c5cd3b4d..90eef63e2c 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -191,10 +191,13 @@ ARG PILLOW_SIMD_VERSION # so when pillow_simd is installed, other packages won't later override it COPY pillow_stub /tmp/pillow_stub -RUN pip${PYTHON_VERSION} install --no-cache-dir --upgrade /tmp/pillow_stub && \ - pip${PYTHON_VERSION} install --no-cache-dir --upgrade pillow_simd==${PILLOW_SIMD_VERSION} && \ - rm -rf /tmp/pillow_stub - +RUN if [ "$TARGETARCH" = "amd64" ]; then \ + pip${PYTHON_VERSION} install --no-cache-dir --upgrade /tmp/pillow_stub && \ + pip${PYTHON_VERSION} install --no-cache-dir --upgrade pillow_simd==${PILLOW_SIMD_VERSION} && \ + rm -rf /tmp/pillow_stub; \ + else \ + pip${PYTHON_VERSION} install --no-cache-dir --upgrade Pillow==${PILLOW_PSEUDOVERSION}; \ + fi ################# # Install Pytorch ################# From b7ed5437c7196081cae1c36466aca1905ebdc4ec Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 16:39:11 -0500 Subject: [PATCH 12/21] python 3.11 --- docker/build_matrix.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index 2b717ab383..baa19709bf 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -242,7 +242,7 @@ IMAGE_NAME: composer-0-22-0-cpu MOFED_VERSION: 5.5-1.0.3.2 NVIDIA_REQUIRE_CUDA_OVERRIDE: '' - PYTHON_VERSION: '3.8' + PYTHON_VERSION: '3.11' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' PYTORCH_VERSION: 2.3.0 From 32f39b950f912c6fb3b33faaaf32c08e510d5875 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 17:14:04 -0500 Subject: [PATCH 13/21] try different target --- docker/Dockerfile | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index 90eef63e2c..f784759218 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -212,10 +212,16 @@ ENV PYTORCH_NIGHTLY_URL=${PYTORCH_NIGHTLY_URL} ENV PYTORCH_NIGHTLY_VERSION=${PYTORCH_NIGHTLY_VERSION} RUN if [ -z "$PYTORCH_NIGHTLY_URL" ] ; then \ - CUDA_VERSION_TAG=$(python${PYTHON_VERSION} -c "print('cu' + ''.join('${CUDA_VERSION}'.split('.')[:2]) if '${CUDA_VERSION}' else 'cpu')") && \ - pip${PYTHON_VERSION} install --no-cache-dir --find-links https://download.pytorch.org/whl/torch_stable.html \ - torch==${PYTORCH_VERSION}+${CUDA_VERSION_TAG} \ - torchvision==${TORCHVISION_VERSION}+${CUDA_VERSION_TAG} ; \ + if [ "$TARGETARCH" = "amd64" ]; then \ + CUDA_VERSION_TAG=$(python${PYTHON_VERSION} -c "print('cu' + ''.join('${CUDA_VERSION}'.split('.')[:2]) if '${CUDA_VERSION}' else 'cpu')") && \ + pip${PYTHON_VERSION} install --no-cache-dir --find-links https://download.pytorch.org/whl/torch_stable.html \ + torch==${PYTORCH_VERSION}+${CUDA_VERSION_TAG} \ + torchvision==${TORCHVISION_VERSION}+${CUDA_VERSION_TAG} ; \ + else \ + CUDA_VERSION_TAG=$(python${PYTHON_VERSION} -c "print('cu' + ''.join('${CUDA_VERSION}'.split('.')[:2]) if '${CUDA_VERSION}' else 'cpu')") && \ + pip${PYTHON_VERSION} install --no-cache-dir --find-links https://download.pytorch.org/whl/cpu/fbgemm_gpu-0.5.0%2Bcpu-cp310-cp310-manylinux2014_aarch64.whl \ + torch==${PYTORCH_VERSION}+${CUDA_VERSION_TAG} \ + torchvision==${TORCHVISION_VERSION}+${CUDA_VERSION_TAG} ; \ else \ pip${PYTHON_VERSION} install --no-cache-dir --pre --index-url ${PYTORCH_NIGHTLY_URL} \ torch==${PYTORCH_VERSION}.${PYTORCH_NIGHTLY_VERSION} \ From 74e6565ce07a5a22ad21e94da4fa11c8e7e2682a Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 17:52:20 -0500 Subject: [PATCH 14/21] remove +cpu from torch arm install --- docker/Dockerfile | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index f784759218..a452bbc67d 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -218,10 +218,9 @@ RUN if [ -z "$PYTORCH_NIGHTLY_URL" ] ; then \ torch==${PYTORCH_VERSION}+${CUDA_VERSION_TAG} \ torchvision==${TORCHVISION_VERSION}+${CUDA_VERSION_TAG} ; \ else \ - CUDA_VERSION_TAG=$(python${PYTHON_VERSION} -c "print('cu' + ''.join('${CUDA_VERSION}'.split('.')[:2]) if '${CUDA_VERSION}' else 'cpu')") && \ - pip${PYTHON_VERSION} install --no-cache-dir --find-links https://download.pytorch.org/whl/cpu/fbgemm_gpu-0.5.0%2Bcpu-cp310-cp310-manylinux2014_aarch64.whl \ - torch==${PYTORCH_VERSION}+${CUDA_VERSION_TAG} \ - torchvision==${TORCHVISION_VERSION}+${CUDA_VERSION_TAG} ; \ + pip${PYTHON_VERSION} install --no-cache-dir --find-links https://download.pytorch.org/whl/cpu/torch_stable.html \ + torch==${PYTORCH_VERSION} \ + torchvision==${TORCHVISION_VERSION} ; \ else \ pip${PYTHON_VERSION} install --no-cache-dir --pre --index-url ${PYTORCH_NIGHTLY_URL} \ torch==${PYTORCH_VERSION}.${PYTORCH_NIGHTLY_VERSION} \ From 7512400ed25a62a6e9c466097058efa470a0776a Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 18:07:43 -0500 Subject: [PATCH 15/21] missed fi --- docker/Dockerfile | 1 + 1 file changed, 1 insertion(+) diff --git a/docker/Dockerfile b/docker/Dockerfile index a452bbc67d..019d0e8dce 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -221,6 +221,7 @@ RUN if [ -z "$PYTORCH_NIGHTLY_URL" ] ; then \ pip${PYTHON_VERSION} install --no-cache-dir --find-links https://download.pytorch.org/whl/cpu/torch_stable.html \ torch==${PYTORCH_VERSION} \ torchvision==${TORCHVISION_VERSION} ; \ + fi ; \ else \ pip${PYTHON_VERSION} install --no-cache-dir --pre --index-url ${PYTORCH_NIGHTLY_URL} \ torch==${PYTORCH_VERSION}.${PYTORCH_NIGHTLY_VERSION} \ From 4eef39741d9333e193a8cc1d2548dbd4001979c1 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Thu, 16 May 2024 18:23:19 -0500 Subject: [PATCH 16/21] ubuntu20.04-aarch64.tgz --- docker/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index 019d0e8dce..cdd49539a9 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -280,7 +280,7 @@ ARG MOFED_VERSION RUN if [ -n "$MOFED_VERSION" ] ; then \ mkdir -p /tmp/mofed && \ - wget -nv -P /tmp/mofed http://content.mellanox.com/ofed/MLNX_OFED-${MOFED_VERSION}/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu22.04-aarch64.tgz && \ + wget -nv -P /tmp/mofed http://content.mellanox.com/ofed/MLNX_OFED-${MOFED_VERSION}/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-aarch64.tgz&& \ tar -zxvf /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-aarch64.tgz -C /tmp/mofed && \ /tmp/mofed/MLNX_OFED_LINUX-${MOFED_VERSION}-ubuntu20.04-aarch64/mlnxofedinstall --user-space-only --without-fw-update --force && \ rm -rf /tmp/mofed ; \ From 3e8d61846f6b2b418189946187cd94d1cc777812 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Fri, 17 May 2024 11:39:22 -0500 Subject: [PATCH 17/21] try cuda --- docker/build_matrix.yaml | 60 ++++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 30 deletions(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index baa19709bf..aed3ec2e3a 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -206,37 +206,37 @@ # - mosaicml/pytorch:2.1.2_cpu-python3.10-ubuntu20.04 # TARGET: pytorch_stage # TORCHVISION_VERSION: 0.16.2 -# - AWS_OFI_NCCL_VERSION: '' -# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 -# COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 -# CUDA_VERSION: 12.1.1 -# IMAGE_NAME: composer-0-22-0 -# MOFED_VERSION: 5.5-1.0.3.2 -# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 -# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 -# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 -# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 -# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 -# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 -# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 -# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 -# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 -# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 -# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 -# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 -# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 -# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 -# PYTHON_VERSION: '3.11' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.3.0 -# TAGS: -# - mosaicml/composer:0.22.0 -# - mosaicml/composer:latest -# TARGET: composer_stage -# TORCHVISION_VERSION: 0.18.0 - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: arm64v8/ubuntu:20.04 + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 + CUDA_VERSION: 12.1.1 + IMAGE_NAME: composer-0-22-0 + MOFED_VERSION: 5.5-1.0.3.2 + NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 + brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 + brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 + brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 + brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 + brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 + brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 + brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 + brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 + brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 + brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 + brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 + brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 + brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 + PYTHON_VERSION: '3.11' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.3.0 + TAGS: + - mosaicml/composer:0.22.0 + - mosaicml/composer:latest + TARGET: composer_stage + TORCHVISION_VERSION: 0.18.0 +- AWS_OFI_NCCL_VERSION: '' + BASE_IMAGE: arm64/ubuntu:20.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 CUDA_VERSION: '' IMAGE_NAME: composer-0-22-0-cpu From b7249a15cecd7c8fb395c60a1136dda14c9ea681 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn Date: Fri, 17 May 2024 11:48:23 -0500 Subject: [PATCH 18/21] remove arm64v8 --- docker/build_matrix.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index aed3ec2e3a..c645f578c5 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -236,7 +236,7 @@ TARGET: composer_stage TORCHVISION_VERSION: 0.18.0 - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: arm64/ubuntu:20.04 + BASE_IMAGE: ubuntu:20.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 CUDA_VERSION: '' IMAGE_NAME: composer-0-22-0-cpu From f73a4af93dd28e90cc23f7035c360222a93b564a Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Fri, 17 May 2024 13:05:06 -0500 Subject: [PATCH 19/21] Update build_matrix.yaml --- docker/build_matrix.yaml | 414 +++++++++++++++++++-------------------- 1 file changed, 207 insertions(+), 207 deletions(-) diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index c645f578c5..bf743a4ca2 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -1,211 +1,211 @@ # This file is automatically generated by generate_build_matrix.py. DO NOT EDIT! -# - AWS_OFI_NCCL_VERSION: '' -# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 -# CUDA_VERSION: 12.1.1 -# IMAGE_NAME: torch-2-3-0-cu121 -# MOFED_VERSION: 5.5-1.0.3.2 -# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 -# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 -# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 -# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 -# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 -# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 -# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 -# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 -# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 -# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 -# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 -# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 -# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 -# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 -# PYTHON_VERSION: '3.11' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.3.0 -# TAGS: -# - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04 -# - mosaicml/pytorch:latest -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.18.0 -# - AWS_OFI_NCCL_VERSION: v1.9.1-aws -# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 -# CUDA_VERSION: 12.1.1 -# IMAGE_NAME: torch-2-3-0-cu121-aws -# MOFED_VERSION: '' -# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 -# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 -# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 -# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 -# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 -# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 -# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 -# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 -# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 -# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 -# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 -# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 -# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 -# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 -# PYTHON_VERSION: '3.11' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.3.0 -# TAGS: -# - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04-aws -# - mosaicml/pytorch:latest-aws -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.18.0 -# - AWS_OFI_NCCL_VERSION: '' -# BASE_IMAGE: ubuntu:20.04 -# CUDA_VERSION: '' -# IMAGE_NAME: torch-2-3-0-cpu -# MOFED_VERSION: '' -# NVIDIA_REQUIRE_CUDA_OVERRIDE: '' -# PYTHON_VERSION: '3.11' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.3.0 -# TAGS: -# - mosaicml/pytorch:2.3.0_cpu-python3.11-ubuntu20.04 -# - mosaicml/pytorch:latest_cpu -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.18.0 -# - AWS_OFI_NCCL_VERSION: '' -# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 -# CUDA_VERSION: 12.1.1 -# IMAGE_NAME: torch-2-2-2-cu121 -# MOFED_VERSION: 5.5-1.0.3.2 -# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 -# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 -# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 -# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 -# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 -# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 -# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 -# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 -# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 -# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 -# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 -# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 -# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 -# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 -# PYTHON_VERSION: '3.11' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.2.2 -# TAGS: -# - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04 -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.17.2 -# - AWS_OFI_NCCL_VERSION: v1.9.1-aws -# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 -# CUDA_VERSION: 12.1.1 -# IMAGE_NAME: torch-2-2-2-cu121-aws -# MOFED_VERSION: '' -# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 -# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 -# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 -# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 -# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 -# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 -# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 -# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 -# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 -# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 -# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 -# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 -# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 -# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 -# PYTHON_VERSION: '3.11' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.2.2 -# TAGS: -# - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04-aws -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.17.2 -# - AWS_OFI_NCCL_VERSION: '' -# BASE_IMAGE: ubuntu:20.04 -# CUDA_VERSION: '' -# IMAGE_NAME: torch-2-2-2-cpu -# MOFED_VERSION: '' -# NVIDIA_REQUIRE_CUDA_OVERRIDE: '' -# PYTHON_VERSION: '3.11' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.2.2 -# TAGS: -# - mosaicml/pytorch:2.2.2_cpu-python3.11-ubuntu20.04 -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.17.2 -# - AWS_OFI_NCCL_VERSION: '' -# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 -# CUDA_VERSION: 12.1.1 -# IMAGE_NAME: torch-2-1-2-cu121 -# MOFED_VERSION: 5.5-1.0.3.2 -# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 -# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 -# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 -# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 -# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 -# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 -# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 -# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 -# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 -# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 -# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 -# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 -# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 -# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 -# PYTHON_VERSION: '3.10' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.1.2 -# TAGS: -# - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04 -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.16.2 -# - AWS_OFI_NCCL_VERSION: v1.9.1-aws -# BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 -# CUDA_VERSION: 12.1.1 -# IMAGE_NAME: torch-2-1-2-cu121-aws -# MOFED_VERSION: '' -# NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 -# brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 -# brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 -# brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 -# brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 -# brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 -# brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 -# brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 -# brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 -# brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 -# brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 -# brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 -# brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 -# brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 -# PYTHON_VERSION: '3.10' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.1.2 -# TAGS: -# - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04-aws -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.16.2 -# - AWS_OFI_NCCL_VERSION: '' -# BASE_IMAGE: ubuntu:20.04 -# CUDA_VERSION: '' -# IMAGE_NAME: torch-2-1-2-cpu -# MOFED_VERSION: '' -# NVIDIA_REQUIRE_CUDA_OVERRIDE: '' -# PYTHON_VERSION: '3.10' -# PYTORCH_NIGHTLY_URL: '' -# PYTORCH_NIGHTLY_VERSION: '' -# PYTORCH_VERSION: 2.1.2 -# TAGS: -# - mosaicml/pytorch:2.1.2_cpu-python3.10-ubuntu20.04 -# TARGET: pytorch_stage -# TORCHVISION_VERSION: 0.16.2 +- AWS_OFI_NCCL_VERSION: '' + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 + IMAGE_NAME: torch-2-3-0-cu121 + MOFED_VERSION: 5.5-1.0.3.2 + NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 + brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 + brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 + brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 + brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 + brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 + brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 + brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 + brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 + brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 + brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 + brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 + brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 + brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 + PYTHON_VERSION: '3.11' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.3.0 + TAGS: + - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04 + - mosaicml/pytorch:latest + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.18.0 +- AWS_OFI_NCCL_VERSION: v1.9.1-aws + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 + IMAGE_NAME: torch-2-3-0-cu121-aws + MOFED_VERSION: '' + NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 + brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 + brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 + brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 + brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 + brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 + brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 + brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 + brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 + brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 + brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 + brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 + brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 + brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 + PYTHON_VERSION: '3.11' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.3.0 + TAGS: + - mosaicml/pytorch:2.3.0_cu121-python3.11-ubuntu20.04-aws + - mosaicml/pytorch:latest-aws + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.18.0 +- AWS_OFI_NCCL_VERSION: '' + BASE_IMAGE: ubuntu:20.04 + CUDA_VERSION: '' + IMAGE_NAME: torch-2-3-0-cpu + MOFED_VERSION: '' + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' + PYTHON_VERSION: '3.11' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.3.0 + TAGS: + - mosaicml/pytorch:2.3.0_cpu-python3.11-ubuntu20.04 + - mosaicml/pytorch:latest_cpu + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.18.0 +- AWS_OFI_NCCL_VERSION: '' + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 + IMAGE_NAME: torch-2-2-2-cu121 + MOFED_VERSION: 5.5-1.0.3.2 + NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 + brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 + brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 + brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 + brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 + brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 + brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 + brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 + brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 + brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 + brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 + brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 + brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 + brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 + PYTHON_VERSION: '3.11' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.2.2 + TAGS: + - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04 + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.17.2 +- AWS_OFI_NCCL_VERSION: v1.9.1-aws + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 + IMAGE_NAME: torch-2-2-2-cu121-aws + MOFED_VERSION: '' + NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 + brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 + brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 + brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 + brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 + brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 + brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 + brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 + brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 + brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 + brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 + brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 + brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 + brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 + PYTHON_VERSION: '3.11' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.2.2 + TAGS: + - mosaicml/pytorch:2.2.2_cu121-python3.11-ubuntu20.04-aws + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.17.2 +- AWS_OFI_NCCL_VERSION: '' + BASE_IMAGE: ubuntu:20.04 + CUDA_VERSION: '' + IMAGE_NAME: torch-2-2-2-cpu + MOFED_VERSION: '' + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' + PYTHON_VERSION: '3.11' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.2.2 + TAGS: + - mosaicml/pytorch:2.2.2_cpu-python3.11-ubuntu20.04 + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.17.2 +- AWS_OFI_NCCL_VERSION: '' + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 + IMAGE_NAME: torch-2-1-2-cu121 + MOFED_VERSION: 5.5-1.0.3.2 + NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 + brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 + brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 + brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 + brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 + brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 + brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 + brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 + brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 + brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 + brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 + brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 + brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 + brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 + PYTHON_VERSION: '3.10' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.1.2 + TAGS: + - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04 + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.16.2 +- AWS_OFI_NCCL_VERSION: v1.9.1-aws + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 + IMAGE_NAME: torch-2-1-2-cu121-aws + MOFED_VERSION: '' + NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471 + brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 + brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 + brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 + brand=tesla,driver>=510,driver<511 brand=unknown,driver>=510,driver<511 brand=nvidia,driver>=510,driver<511 + brand=nvidiartx,driver>=510,driver<511 brand=geforce,driver>=510,driver<511 brand=geforcertx,driver>=510,driver<511 + brand=quadro,driver>=510,driver<511 brand=quadrortx,driver>=510,driver<511 brand=titan,driver>=510,driver<511 + brand=titanrtx,driver>=510,driver<511 brand=tesla,driver>=515,driver<516 brand=unknown,driver>=515,driver<516 + brand=nvidia,driver>=515,driver<516 brand=nvidiartx,driver>=515,driver<516 brand=geforce,driver>=515,driver<516 + brand=geforcertx,driver>=515,driver<516 brand=quadro,driver>=515,driver<516 brand=quadrortx,driver>=515,driver<516 + brand=titan,driver>=515,driver<516 brand=titanrtx,driver>=515,driver<516 brand=tesla,driver>=525,driver<526 + brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 + brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 + brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 + PYTHON_VERSION: '3.10' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.1.2 + TAGS: + - mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04-aws + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.16.2 +- AWS_OFI_NCCL_VERSION: '' + BASE_IMAGE: ubuntu:20.04 + CUDA_VERSION: '' + IMAGE_NAME: torch-2-1-2-cpu + MOFED_VERSION: '' + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' + PYTHON_VERSION: '3.10' + PYTORCH_NIGHTLY_URL: '' + PYTORCH_NIGHTLY_VERSION: '' + PYTORCH_VERSION: 2.1.2 + TAGS: + - mosaicml/pytorch:2.1.2_cpu-python3.10-ubuntu20.04 + TARGET: pytorch_stage + TORCHVISION_VERSION: 0.16.2 - AWS_OFI_NCCL_VERSION: '' BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.22.0 From 4763e0d1d130851e00bbe8b5413f82e96b022a36 Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Sat, 18 May 2024 03:03:30 -0500 Subject: [PATCH 20/21] test arm64 --- docker/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index cdd49539a9..a9f92a887e 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -93,7 +93,7 @@ RUN if [ -n "$CUDA_VERSION" ] ; then \ rm -rf /var/lib/apt/lists/* \ apt-key del 7fa2af80 && \ mkdir -p /tmp/cuda-keyring && \ - wget -P /tmp/cuda-keyring https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb && \ + wget -P /tmp/cuda-keyring https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/arm64/cuda-keyring_1.0-1_all.deb && \ dpkg -i /tmp/cuda-keyring/cuda-keyring_1.0-1_all.deb && \ rm -rf /tmp/cuda-keyring ; \ fi From fb9e44042df933e4a7e2770ee26ffe122ceccc0e Mon Sep 17 00:00:00 2001 From: Kevin DeShawn <126115026+KevDevSha@users.noreply.github.com> Date: Sat, 18 May 2024 03:37:09 -0500 Subject: [PATCH 21/21] Update docker-configure-build-push.yaml --- .github/workflows/docker-configure-build-push.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/docker-configure-build-push.yaml b/.github/workflows/docker-configure-build-push.yaml index 61993a435a..819650d51a 100644 --- a/.github/workflows/docker-configure-build-push.yaml +++ b/.github/workflows/docker-configure-build-push.yaml @@ -36,7 +36,7 @@ on: required: true jobs: configure-build-push: - runs-on: mosaic-4wide + runs-on: mosaic-8wide steps: - name: Maximize Build Space on Worker uses: easimon/maximize-build-space@v4