diff --git a/docker/README.md b/docker/README.md index 736bbbd70d..3de635a74b 100644 --- a/docker/README.md +++ b/docker/README.md @@ -32,11 +32,11 @@ To install composer, once inside the image, run `pip install mosaicml`. |----------------|----------|-------------------|---------------------|------------------|------------------------------------------------------------------------------------------| | Ubuntu 20.04 | Base | 2.3.0 | 12.1.0 (Infiniband) | 3.11 | `mosaicml/pytorch:2.3.0_cu121-nightly20240110-python3.11-ubuntu20.04` | | Ubuntu 20.04 | Base | 2.3.0 | 12.1.0 (EFA) | 3.11 | `mosaicml/pytorch:2.3.0_cu121-nightly20240110-python3.11-ubuntu20.04-aws` | -| Ubuntu 20.04 | Base | 2.2.1 | 12.1.0 (Infiniband) | 3.11 | `mosaicml/pytorch:2.2.1_cu121-python3.11-ubuntu20.04` | -| Ubuntu 20.04 | Base | 2.2.1 | 12.1.0 (EFA) | 3.11 | `mosaicml/pytorch:2.2.1_cu121-python3.11-ubuntu20.04-aws` | +| Ubuntu 20.04 | Base | 2.2.1 | 12.1.1 (Infiniband) | 3.11 | `mosaicml/pytorch:2.2.1_cu121-python3.11-ubuntu20.04` | +| Ubuntu 20.04 | Base | 2.2.1 | 12.1.1 (EFA) | 3.11 | `mosaicml/pytorch:2.2.1_cu121-python3.11-ubuntu20.04-aws` | | Ubuntu 20.04 | Base | 2.2.1 | cpu | 3.11 | `mosaicml/pytorch:2.2.1_cpu-python3.11-ubuntu20.04` | -| Ubuntu 20.04 | Base | 2.1.2 | 12.1.0 (Infiniband) | 3.10 | `mosaicml/pytorch:latest`, `mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04` | -| Ubuntu 20.04 | Base | 2.1.2 | 12.1.0 (EFA) | 3.10 | `mosaicml/pytorch:latest-aws`, `mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04-aws` | +| Ubuntu 20.04 | Base | 2.1.2 | 12.1.1 (Infiniband) | 3.10 | `mosaicml/pytorch:latest`, `mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04` | +| Ubuntu 20.04 | Base | 2.1.2 | 12.1.1 (EFA) | 3.10 | `mosaicml/pytorch:latest-aws`, `mosaicml/pytorch:2.1.2_cu121-python3.10-ubuntu20.04-aws` | | Ubuntu 20.04 | Base | 2.1.2 | cpu | 3.10 | `mosaicml/pytorch:latest_cpu`, `mosaicml/pytorch:2.1.2_cpu-python3.10-ubuntu20.04` | | Ubuntu 20.04 | Base | 2.0.1 | 11.8.0 (Infiniband) | 3.10 | `mosaicml/pytorch:2.0.1_cu118-python3.10-ubuntu20.04` | | Ubuntu 20.04 | Base | 2.0.1 | 11.8.0 (EFA) | 3.10 | `mosaicml/pytorch:2.0.1_cu118-python3.10-ubuntu20.04-aws` | diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml index 0f6d827304..994c1da385 100644 --- a/docker/build_matrix.yaml +++ b/docker/build_matrix.yaml @@ -1,23 +1,10 @@ # This file is automatically generated by generate_build_matrix.py. DO NOT EDIT! - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.0 + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 IMAGE_NAME: torch-2-2-1-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 + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' PYTHON_VERSION: '3.11' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' @@ -27,24 +14,11 @@ TARGET: pytorch_stage TORCHVISION_VERSION: 0.17.1 - AWS_OFI_NCCL_VERSION: v1.7.4-aws - BASE_IMAGE: nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.0 + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 + CUDA_VERSION: 12.1.1 IMAGE_NAME: torch-2-2-1-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 + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' PYTHON_VERSION: '3.11' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' @@ -68,24 +42,11 @@ TARGET: pytorch_stage TORCHVISION_VERSION: 0.17.1 - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.0 + 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 + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' PYTHON_VERSION: '3.10' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' @@ -96,24 +57,11 @@ TARGET: pytorch_stage TORCHVISION_VERSION: 0.16.2 - AWS_OFI_NCCL_VERSION: v1.7.4-aws - BASE_IMAGE: nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04 - CUDA_VERSION: 12.1.0 + 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 + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' PYTHON_VERSION: '3.10' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' @@ -245,25 +193,12 @@ TARGET: pytorch_stage TORCHVISION_VERSION: 0.18.0 - AWS_OFI_NCCL_VERSION: '' - BASE_IMAGE: nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04 + BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04 COMPOSER_INSTALL_COMMAND: mosaicml[all]==0.20.1 - CUDA_VERSION: 12.1.0 + CUDA_VERSION: 12.1.1 IMAGE_NAME: composer-0-20-1 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 + NVIDIA_REQUIRE_CUDA_OVERRIDE: '' PYTHON_VERSION: '3.10' PYTORCH_NIGHTLY_URL: '' PYTORCH_NIGHTLY_VERSION: '' diff --git a/docker/generate_build_matrix.py b/docker/generate_build_matrix.py index 10b07610ca..9e3fd7fd15 100644 --- a/docker/generate_build_matrix.py +++ b/docker/generate_build_matrix.py @@ -43,9 +43,9 @@ def _get_cuda_version(pytorch_version: str, use_cuda: bool): if not use_cuda: return '' if pytorch_version == '2.2.1': - return '12.1.0' + return '12.1.1' if pytorch_version == '2.1.2': - return '12.1.0' + return '12.1.1' if pytorch_version == '2.0.1': return '11.8.0' raise ValueError(f'Invalid pytorch_version: {pytorch_version}')