extend pytest-sdist timeout to 30 min for slow/flaky tests (#3456) [skip ci]

* extend pytest-sdist timeout to 30 min for slow/flaky tests

* Also preload the cdn cache so it doesn't get stampeded

* fix yaml syntax

* missing fields

* can't pipe to dev/null

* Fix nightlies and add 2.10.0 to multi-gpu suite

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

@@ -35,12 +35,6 @@ jobs:
             pytorch: 2.8.0
             axolotl_extras: fbgemm-gpu
             num_gpus: 2
-          - cuda: 128
-            cuda_version: 12.8.1
-            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras: "fbgemm-gpu"
-            num_gpus: 2
           - cuda: 129
             cuda_version: 12.9.1
             python_version: "3.12"
@@ -55,6 +49,13 @@ jobs:
             axolotl_extras:
 #            axolotl_extras: fbgemm-gpu
             num_gpus: 2
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.10.0
+            axolotl_extras: "fbgemm-gpu"
+            num_gpus: 2
+            dockerfile: "Dockerfile-uv.jinja"
     runs-on: [self-hosted, modal]
     timeout-minutes: 120
     steps:

.github/workflows/tests-nightly.yml

@@ -18,15 +18,27 @@ jobs:
         env:
           SKIP: no-commit-to-branch
 
+  prime-cdn-s3-cache:
+    name: Prefetch S3 once to prime the CDN cache
+    runs-on: ubuntu-latest
+    if: ${{ !github.event.pull_request.draft }}
+    timeout-minutes: 10
+    steps:
+      - name: Restore Cache from S3
+        id: hf-cache-restore-s3
+        run: |
+          curl -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst > /dev/null
+
   pytest:
     name: PyTest
     runs-on: ubuntu-latest
+    needs: [prime-cdn-s3-cache]
     strategy:
       fail-fast: false
       max-parallel: 2
       matrix:
-        python_version: ["3.11"]
+        python_version: ["3.12"]  # TODO include py3.14 once https://github.com/mistralai/mistral-common/pull/194 is merged
-        pytorch_version: ["2.8.0", "2.9.0", "2.9.1"]
+        pytorch_version: ["2.8.0", "2.9.1", "2.10.0"]
     timeout-minutes: 20
 
     steps:
@@ -102,16 +114,23 @@ jobs:
           - cuda: 128
             cuda_version: 12.8.1
             python_version: "3.11"
-            pytorch: 2.8.0
+            pytorch: 2.9.1
             num_gpus: 1
             axolotl_extras:
             nightly_build: "true"
           - cuda: 128
             cuda_version: 12.8.1
             python_version: "3.11"
+            pytorch: 2.10.0
+            num_gpus: 1
+            axolotl_extras:
+          - cuda: 130
+            cuda_version: 13.0.0
+            python_version: "3.12"
             pytorch: 2.9.1
             num_gpus: 1
             axolotl_extras:
+            dockerfile: "Dockerfile-uv.jinja"
             nightly_build: "true"
     steps:
       - name: Checkout
@@ -132,6 +151,7 @@ jobs:
           echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
           echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
           echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
+          echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
           echo "NIGHTLY_BUILD=${{ matrix.nightly_build }}" >> $GITHUB_ENV
           echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
       - name: Run tests job on Modal

.github/workflows/tests.yml

@@ -46,11 +46,22 @@ jobs:
         env:
           SKIP: no-commit-to-branch
 
+  prime-cdn-s3-cache:
+    name: Prefetch S3 once to prime the CDN cache
+    runs-on: ubuntu-latest
+    if: ${{ !github.event.pull_request.draft }}
+    timeout-minutes: 10
+    steps:
+      - name: Restore Cache from S3
+        id: hf-cache-restore-s3
+        run: |
+          curl -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst > /dev/null
+
   pytest:
     name: PyTest
     runs-on: ubuntu-latest
     if: ${{ !github.event.pull_request.draft }}
-#    needs: [preload-cache]
+    needs: [prime-cdn-s3-cache]
     strategy:
       fail-fast: false
       matrix:
@@ -146,6 +157,7 @@ jobs:
     name: PyTest from Source Dist
     runs-on: ubuntu-latest
     if: ${{ !github.event.pull_request.draft }}
+    needs: [prime-cdn-s3-cache]
     strategy:
       fail-fast: false
       matrix:
@@ -156,7 +168,7 @@ jobs:
 #            pytorch_version: "2.8.0"
 #          - python_version: "3.14"
 #            pytorch_version: "2.9.1"
-    timeout-minutes: 20
+    timeout-minutes: 30
 
     steps:
       - name: cleanup node