add cu130 + torch 2.9.1 to test matrices (#3343)

* add cu130 + torch 2.9.1 to test matrices

* uv can't use pip3 directly

.github/workflows/multi-gpu-e2e.yml

@@ -43,6 +43,13 @@ jobs:
             axolotl_extras: fbgemm-gpu
             num_gpus: 2
             nightly_build: "true"
+          - cuda: 130
+            cuda_version: 13.0.0
+            python_version: "3.11"
+            pytorch: 2.9.1
+            axolotl_extras: fbgemm-gpu
+            num_gpus: 2
+            nightly_build: "true"
     runs-on: [self-hosted, modal]
     timeout-minutes: 120
     steps:

.github/workflows/tests.yml

@@ -316,6 +316,12 @@ jobs:
             pytorch: 2.9.1
             num_gpus: 1
             axolotl_extras:
+          - cuda: 130
+            cuda_version: 13.0.0
+            python_version: "3.11"
+            pytorch: 2.9.1
+            num_gpus: 1
+            axolotl_extras:
     steps:
       - name: Checkout
         uses: actions/checkout@v4

docker/Dockerfile-uv-base

@@ -39,11 +39,11 @@ RUN case "$PYTORCH_VERSION" in \
         2.9.[0-9]*) \
             if [ "$CUDA" = "128" ]; then \
                 wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
-                uv pip3 install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
+                uv pip install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
                 rm flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
             elif [ "$CUDA" = "130" ]; then \
                 wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
-                uv pip3 install --no-cache-dir flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
+                uv pip install --no-cache-dir flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
                 rm flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
             fi \
             ;; \