[Refactor] Move the Linux CI jobs to OSDC runners (#4530)

Author: huydhn

.github/unittest/linux_libs/scripts_gym/run_all.sh

@@ -206,7 +206,7 @@ run_tests() {
         test_failed=1
     fi
 
-    if ! python .github/unittest/helpers/coverage_run_parallel.py -m pytest test/libs --instafail -v --durations 200 -k "gym and not isaac" --mp_fork; then
+    if ! python .github/unittest/helpers/coverage_run_parallel.py -m pytest test/libs --instafail -v --durations 200 -k "gym and not isaac" --mp_fork_if_no_cuda; then
         echo "ERROR: test/libs failed for ${version_name}"
         test_failed=1
     fi

.github/workflows/benchmarks.yml

@@ -66,7 +66,7 @@ jobs:
     if: github.event_name != 'pull_request'
     needs: validate-report
     name: ${{ matrix.device }} Pytest benchmark
-    runs-on: linux.g5.4xlarge.nvidia.gpu
+    runs-on: mt-l-x86aavx2-11-41-a10g
     timeout-minutes: 120
     strategy:
       fail-fast: false

.github/workflows/benchmarks_pr.yml

@@ -71,7 +71,7 @@ jobs:
   prepare-environment:
     name: Prepare pinned benchmark environment
     if: contains(github.event.pull_request.labels.*.name, 'benchmarks/upload')
-    runs-on: linux.g5.4xlarge.nvidia.gpu
+    runs-on: mt-l-x86aavx2-11-41-a10g
     container:
       image: nvidia/cuda:12.6.3-cudnn-devel-ubuntu22.04@sha256:b3e7fba84d169f46939f00c25be7d016f712a8d651f4756d6a55e693d84d94f2
       options: --gpus all --shm-size=8g
@@ -153,7 +153,7 @@ jobs:
     name: ${{ matrix.device }} ${{ matrix.revision }} benchmark
     if: contains(github.event.pull_request.labels.*.name, 'benchmarks/upload')
     needs: [prepare-definitions, prepare-environment]
-    runs-on: linux.g5.4xlarge.nvidia.gpu
+    runs-on: mt-l-x86aavx2-11-41-a10g
     strategy:
       fail-fast: false
       max-parallel: 4
@@ -315,7 +315,7 @@ jobs:
               "pr_number": int(os.environ["PR_NUMBER"]),
               "base_sha": os.environ["BASE_SHA"],
               "head_sha": os.environ["HEAD_SHA"],
-              "runner": "linux.g5.4xlarge.nvidia.gpu",
+              "runner": "mt-l-x86aavx2-11-41-a10g",
               "image": os.environ["IMAGE"],
               "python_version": os.environ["PYTHON_VERSION"],
               "system_environment_sha256": os.environ["SYSTEM_ENVIRONMENT_SHA"],

.github/workflows/lint.yml

@@ -22,8 +22,9 @@ permissions:
 
 jobs:
   python-source-and-configs:
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
+      runner: mt-l-x86iavx512-8-64
       repository: pytorch/rl
       script: |
         set -euo pipefail
@@ -50,8 +51,9 @@ jobs:
         echo '::endgroup::'
 
   c-source:
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
+      runner: mt-l-x86iavx512-8-64
       repository: pytorch/rl
       script: |
         set -euo pipefail

.github/workflows/test-linux-examples.yml

@@ -26,11 +26,11 @@ jobs:
         cuda_arch_version: ["13.0"]
         shard: ["1", "2"]
       fail-fast: false
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
-      runner: linux.g5.4xlarge.nvidia.gpu
+      runner: mt-l-x86aavx2-11-41-a10g
       repository: pytorch/rl
-      docker-image: "nvidia/cuda:13.0.2-cudnn-devel-ubuntu24.04"
+      docker-image: "ghcr.io/pytorch/test-infra/osdc-cuda:cuda13.0.3-cudnn-devel-ubuntu24.04"
       gpu-arch-type: cuda
       gpu-arch-version: ${{ matrix.cuda_arch_version }}
       timeout: 120

.github/workflows/test-linux-habitat.yml

@@ -28,11 +28,11 @@ jobs:
         python_version: ["3.10"]
         cuda_arch_version: ["12.8"]
       fail-fast: false
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
-      runner: linux.g5.12xlarge.nvidia.gpu
+      runner: mt-l-x86aavx2-45-167-a10g-4
       repository: pytorch/rl
-      docker-image: "nvidia/cuda:12.8.1-cudnn-devel-ubuntu22.04"
+      docker-image: "ghcr.io/pytorch/test-infra/osdc-cuda:cuda12.8.1-cudnn-devel-ubuntu24.04"
       gpu-arch-type: cuda
       gpu-arch-version: ${{ matrix.cuda_arch_version }}
       timeout: 90

.github/workflows/test-linux-libs.yml

@@ -29,11 +29,11 @@ jobs:
       matrix:
         python_version: ["3.12"]
         cuda_arch_version: ["12.9"]
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
       repository: pytorch/rl
-      runner: "linux.g6.4xlarge.experimental.nvidia.gpu"
-      docker-image: "pytorch/pytorch:2.8.0-cuda12.9-cudnn9-devel"
+      runner: "mt-l-x86aavx2-11-41-l4"
+      docker-image: "ghcr.io/pytorch/test-infra/osdc-cuda:cuda12.9.2-cudnn-devel-ubuntu24.04"
       timeout: 60
       script: |
         if [[ "${{ github.ref }}" =~ release/* ]]; then
@@ -72,11 +72,11 @@ jobs:
       matrix:
         python_version: ["3.12"]
         cuda_arch_version: ["12.9"]
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
       repository: pytorch/rl
-      runner: "linux.g6.4xlarge.experimental.nvidia.gpu"
-      docker-image: "pytorch/pytorch:2.8.0-cuda12.9-cudnn9-devel"
+      runner: "mt-l-x86aavx2-11-41-l4"
+      docker-image: "ghcr.io/pytorch/test-infra/osdc-cuda:cuda12.9.2-cudnn-devel-ubuntu24.04"
       timeout: 60
       script: |
         if [[ "${{ github.ref }}" =~ release/* ]]; then

.github/workflows/test-linux-llm.yml

@@ -37,13 +37,13 @@ jobs:
       matrix:
         python_version: ["3.11"]
         cuda_arch_version: ["12.8"]
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
       repository: pytorch/rl
-      runner: "linux.g5.4xlarge.nvidia.gpu"
+      runner: "mt-l-x86aavx2-11-41-a10g"
       gpu-arch-type: cuda
       gpu-arch-version: "12.8"
-      docker-image: "nvidia/cuda:12.8.0-devel-ubuntu22.04"
+      docker-image: "ghcr.io/pytorch/test-infra/osdc-cuda:cuda12.8.1-cudnn-devel-ubuntu24.04"
       timeout: 90
       script: |
         if [[ "${{ github.ref }}" =~ release/* ]]; then

.github/workflows/test-linux-mujoco.yml

@@ -33,11 +33,11 @@ jobs:
         # filtering in .github/unittest/linux_sota/scripts/test_sota.py.
         shard: ["1", "2"]
       fail-fast: false
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job_v3.yml@main
     with:
-      runner: linux.g5.4xlarge.nvidia.gpu
+      runner: mt-l-x86aavx2-11-41-a10g
       repository: pytorch/rl
-      docker-image: "nvidia/cuda:13.0.2-cudnn-devel-ubuntu24.04"
+      docker-image: "ghcr.io/pytorch/test-infra/osdc-cuda:cuda13.0.3-cudnn-devel-ubuntu24.04"
       gpu-arch-type: cuda
       gpu-arch-version: ${{ matrix.cuda_arch_version }}
       timeout: 90