Add H100 to Float8 CI for testing

.github/workflows/float8_test.yml

@@ -28,7 +28,15 @@ jobs:
             torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cu121'
             gpu-arch-type: "cuda"
             gpu-arch-version: "12.1"
+          - name: H100
+            runs-on: linux.aws.h100
+            torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cu121'
+            gpu-arch-type: "cuda"
+            gpu-arch-version: "12.1"
 
+    permissions:
+      id-token: write
+      contents: read
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     with:
       timeout: 60

.github/workflows/nightly_smoke_test.yml

@@ -11,7 +11,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  HF_TOKEN: ${{ secrets.HF_TOKEN }} 
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
 
 jobs:
   test:
@@ -25,7 +25,9 @@ jobs:
             gpu-arch-type: "cuda"
             gpu-arch-version: "12.1"
 
-
+    permissions:
+      id-token: write
+      contents: read
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     with:
       runner: ${{ matrix.runs-on }}

.github/workflows/regression_test.yml

@@ -34,6 +34,9 @@ jobs:
             gpu-arch-type: "cpu"
             gpu-arch-version: ""
 
+    permissions:
+      id-token: write
+      contents: read
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     with:
       timeout: 120
@@ -87,6 +90,11 @@ jobs:
             torch-spec: 'torch==2.5.1 --index-url https://download.pytorch.org/whl/cpu'
             gpu-arch-type: "cpu"
             gpu-arch-version: ""
+          - name: H100
+            runs-on: linux.aws.h100
+            torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cu121'
+            gpu-arch-type: "cuda"
+            gpu-arch-version: "12.1"
 
     uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     with: