add 12.8.1 cuda to the base matrix (#2426)

* add 12.8.1 cuda to the base matrix

* use nightly

* bump deepspeed and set no binary

* deepspeed binary fixes hopefully

* install deepspeed by itself

* multiline fix

* make sure ninja is installed

* try with reversion of packaging/setuptools/wheel install

* use license instead of license-file

* try rolling back packaging and setuptools versions

* comment out license for validation for now

* make sure packaging version is consistent

* more parity across tests and docker images for packaging/setuptools

.github/workflows/base.yml

@@ -40,6 +40,12 @@ jobs:
             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"
+          - cuda: "128"
+            cuda_version: 12.8.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: nightly
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -61,7 +67,7 @@ jobs:
         uses: docker/build-push-action@v4
         with:
           context: .
-          file: ./docker/Dockerfile-base
+          file: ${{ matrix.pytorch == 'nightly' && './docker/Dockerfile-base-nightly' || './docker/Dockerfile-base' }}
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           labels: ${{ steps.metadata.outputs.labels }}