Migrate A100 CUDA CI jobs to OSDC runners

Move the A100-dependent jobs in cuda.yml (export-model-cuda-artifact,
test-model-cuda-e2e) and cuda-perf.yml (export-models, benchmark-cuda)
from pytorch/test-infra linux_job_v2 (AWS) to linux_job_v3 (OSDC/ARC).
Runner labels are remapped per pytorch/.github/arc.yaml:
linux.aws.a100 -> mt-l-x86iavx512-11-125-a100 and the A10G fallback
linux.g5.4xlarge.nvidia.gpu -> mt-l-x86aavx2-29-113-a10g.

Jobs that never run on A100 stay on linux_job_v2 / linux.g5.4xlarge.nvidia.gpu.

Authored with Claude Code.

Author: huydhn

.github/workflows/cuda-perf.yml

@@ -124,7 +124,7 @@ jobs:
   export-models:
     name: export-models
     needs: set-parameters
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     permissions:
       id-token: write
       contents: read
@@ -135,7 +135,7 @@ jobs:
     with:
       timeout: 90
       secrets-env: EXECUTORCH_HF_TOKEN
-      runner: ${{ contains(matrix.model, 'Qwen3.5-35B-A3B') && 'linux.aws.a100' || 'linux.g5.4xlarge.nvidia.gpu' }}
+      runner: ${{ contains(matrix.model, 'Qwen3.5-35B-A3B') && 'mt-l-x86iavx512-11-125-a100' || 'mt-l-x86aavx2-29-113-a10g' }}
       gpu-arch-type: cuda
       gpu-arch-version: "13.0"
       use-custom-docker-registry: false
@@ -192,7 +192,7 @@ jobs:
         contains(needs.changed-files.outputs.changed-files, '.ci/scripts/test_model_e2e.sh') ||
         needs.run-decision.outputs.is-full-run == 'true'
       )
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     permissions:
       id-token: write
       contents: read
@@ -201,7 +201,7 @@ jobs:
       fail-fast: false
     with:
       timeout: 90
-      runner: ${{ contains(matrix.model, 'Qwen3.5-35B-A3B') && 'linux.aws.a100' || 'linux.g5.4xlarge.nvidia.gpu' }}
+      runner: ${{ contains(matrix.model, 'Qwen3.5-35B-A3B') && 'mt-l-x86iavx512-11-125-a100' || 'mt-l-x86aavx2-29-113-a10g' }}
       gpu-arch-type: cuda
       gpu-arch-version: "13.0"
       use-custom-docker-registry: false

.github/workflows/cuda.yml

@@ -229,7 +229,7 @@ jobs:
         contains(needs.changed-files.outputs.changed-files, '.ci/scripts/test_model_e2e.sh') ||
         needs.run-decision.outputs.is-full-run == 'true'
       )
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     permissions:
       id-token: write
       contents: read
@@ -342,7 +342,7 @@ jobs:
     with:
       timeout: 150
       secrets-env: EXECUTORCH_HF_TOKEN
-      runner: ${{ (matrix.model.name == 'Qwen3.5-35B-A3B-HQQ-INT4' || matrix.model.name == 'gemma-4-31B-it-HQQ-INT4') && 'linux.aws.a100' || 'linux.g5.4xlarge.nvidia.gpu' }}
+      runner: ${{ (matrix.model.name == 'Qwen3.5-35B-A3B-HQQ-INT4' || matrix.model.name == 'gemma-4-31B-it-HQQ-INT4') && 'mt-l-x86iavx512-11-125-a100' || 'mt-l-x86aavx2-29-113-a10g' }}
       gpu-arch-type: cuda
       gpu-arch-version: "13.0"
       use-custom-docker-registry: false
@@ -390,7 +390,7 @@ jobs:
         contains(needs.changed-files.outputs.changed-files, '.ci/scripts/test_model_e2e.sh') ||
         needs.run-decision.outputs.is-full-run == 'true'
       )
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     permissions:
       id-token: write
       contents: read
@@ -494,7 +494,7 @@ jobs:
             quant: "non-quantized"
     with:
       timeout: 90
-      runner: ${{ (matrix.model.name == 'Qwen3.5-35B-A3B-HQQ-INT4' || matrix.model.name == 'gemma-4-31B-it-HQQ-INT4') && 'linux.aws.a100' || 'linux.g5.4xlarge.nvidia.gpu' }}
+      runner: ${{ (matrix.model.name == 'Qwen3.5-35B-A3B-HQQ-INT4' || matrix.model.name == 'gemma-4-31B-it-HQQ-INT4') && 'mt-l-x86iavx512-11-125-a100' || 'mt-l-x86aavx2-29-113-a10g' }}
       gpu-arch-type: cuda
       gpu-arch-version: "13.0"
       use-custom-docker-registry: false