diff --git a/.github/workflows/base.yml b/.github/workflows/base.yml index 160ed7df9..7af6059c8 100644 --- a/.github/workflows/base.yml +++ b/.github/workflows/base.yml @@ -25,20 +25,6 @@ jobs: fail-fast: false matrix: include: - - cuda: "124" - cuda_version: 12.4.1 - cudnn_version: "" - python_version: "3.11" - pytorch: 2.6.0 - torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX" - dockerfile: "Dockerfile-base" - - cuda: "126" - cuda_version: 12.6.3 - cudnn_version: "" - python_version: "3.11" - pytorch: 2.6.0 - torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX" - dockerfile: "Dockerfile-base" - cuda: "126" cuda_version: 12.6.3 cudnn_version: "" @@ -122,13 +108,6 @@ jobs: fail-fast: false matrix: include: - - cuda: "126" - cuda_version: 12.6.3 - cudnn_version: "" - python_version: "3.11" - pytorch: 2.6.0 - torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX" - dockerfile: "Dockerfile-uv-base" - cuda: "126" cuda_version: 12.6.3 cudnn_version: "" diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 3f98dd2b4..4040ccdc9 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -15,11 +15,6 @@ jobs: fail-fast: false matrix: include: - - cuda: 126 - cuda_version: 12.6.3 - python_version: "3.11" - pytorch: 2.6.0 - axolotl_extras: - cuda: 126 cuda_version: 12.6.3 python_version: "3.11" @@ -88,11 +83,6 @@ jobs: strategy: matrix: include: - - cuda: 126 - cuda_version: 12.6.3 - python_version: "3.11" - pytorch: 2.6.0 - axolotl_extras: - cuda: 126 cuda_version: 12.6.3 python_version: "3.11" @@ -162,11 +152,6 @@ jobs: strategy: matrix: include: - - cuda: 126 - cuda_version: 12.6.3 - python_version: "3.11" - pytorch: 2.6.0 - axolotl_extras: - cuda: 126 cuda_version: 12.6.3 python_version: "3.11" diff --git a/.github/workflows/multi-gpu-e2e.yml b/.github/workflows/multi-gpu-e2e.yml index 05f9e0761..6a92de352 100644 --- a/.github/workflows/multi-gpu-e2e.yml +++ b/.github/workflows/multi-gpu-e2e.yml @@ -26,13 +26,6 @@ jobs: fail-fast: false matrix: include: - - cuda: 126 - cuda_version: 12.6.3 - python_version: "3.11" - pytorch: 2.6.0 - axolotl_extras: - num_gpus: 2 - nightly_build: "true" - cuda: 126 cuda_version: 12.6.3 python_version: "3.11" diff --git a/.github/workflows/nightlies.yml b/.github/workflows/nightlies.yml index 49bce470b..18b036a0d 100644 --- a/.github/workflows/nightlies.yml +++ b/.github/workflows/nightlies.yml @@ -12,16 +12,16 @@ jobs: fail-fast: false matrix: include: - - cuda: 126 - cuda_version: 12.6.3 - python_version: "3.11" - pytorch: 2.6.0 - axolotl_extras: - cuda: 126 cuda_version: 12.6.3 python_version: "3.11" pytorch: 2.7.1 axolotl_extras: + - cuda: 128 + cuda_version: 12.8.1 + python_version: "3.11" + pytorch: 2.8.0 + axolotl_extras: runs-on: axolotl-gpu-runner steps: - name: Checkout @@ -65,16 +65,16 @@ jobs: strategy: matrix: include: - - cuda: 126 - cuda_version: 12.6.3 - python_version: "3.11" - pytorch: 2.6.0 - axolotl_extras: - cuda: 126 cuda_version: 12.6.3 python_version: "3.11" pytorch: 2.7.1 axolotl_extras: + - cuda: 128 + cuda_version: 12.8.1 + python_version: "3.11" + pytorch: 2.8.0 + axolotl_extras: runs-on: axolotl-gpu-runner steps: - name: Checkout diff --git a/.github/workflows/tests-nightly.yml b/.github/workflows/tests-nightly.yml index fc6c2b396..35cb707eb 100644 --- a/.github/workflows/tests-nightly.yml +++ b/.github/workflows/tests-nightly.yml @@ -26,7 +26,7 @@ jobs: max-parallel: 2 matrix: python_version: ["3.11"] - pytorch_version: ["2.6.0", "2.7.0"] + pytorch_version: ["2.7.1", "2.8.0"] timeout-minutes: 20 steps: @@ -102,14 +102,14 @@ jobs: - cuda: 126 cuda_version: 12.6.3 python_version: "3.11" - pytorch: 2.6.0 + pytorch: 2.7.1 num_gpus: 1 axolotl_extras: nightly_build: "true" - - cuda: 126 - cuda_version: 12.6.3 + - cuda: 128 + cuda_version: 12.8.1 python_version: "3.11" - pytorch: 2.7.1 + pytorch: 2.8.0 num_gpus: 1 axolotl_extras: nightly_build: "true" diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index 5d5bdb5ac..8f368b517 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -55,7 +55,7 @@ jobs: fail-fast: false matrix: python_version: ["3.11"] - pytorch_version: ["2.6.0", "2.7.1", "2.8.0"] + pytorch_version: ["2.7.1", "2.8.0"] timeout-minutes: 20 steps: @@ -130,7 +130,7 @@ jobs: fail-fast: false matrix: python_version: ["3.11"] - pytorch_version: ["2.6.0", "2.7.1", "2.8.0"] + pytorch_version: ["2.7.1", "2.8.0"] timeout-minutes: 20 steps: @@ -286,12 +286,6 @@ jobs: fail-fast: false matrix: include: - - cuda: 126 - cuda_version: 12.6.3 - python_version: "3.11" - pytorch: 2.6.0 - num_gpus: 1 - axolotl_extras: - cuda: 128 cuda_version: 12.8.1 python_version: "3.11" diff --git a/README.md b/README.md index 1a033acd9..6313a73ca 100644 --- a/README.md +++ b/README.md @@ -73,7 +73,7 @@ Features: - NVIDIA GPU (Ampere or newer for `bf16` and Flash Attention) or AMD GPU - Python 3.11 -- PyTorch ≥2.6.0 +- PyTorch ≥2.7.1 ### Google Colab