diff --git a/.github/workflows/inductor-cu124-unittest.yml b/.github/workflows/inductor-cu124-unittest.yml
new file mode 100644
index 00000000000000..85a367b7dd8329
--- /dev/null
+++ b/.github/workflows/inductor-cu124-unittest.yml
@@ -0,0 +1,82 @@
+# Workflow: Inductor Cu124 Unit Test
+# 1. runs unit tests for inductor-cu124.
+# 2. perfoms daily memory leak checks and reruns of disabled tests, scheduled at `29 8 * * *`.
+name: inductor-cu124-unittest
+
+on:
+  workflow_call:
+  workflow_dispatch:
+  schedule:
+    - cron: 29 8 * * *  # about 1:29am PDT, for mem leak check and rerun disabled tests
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-unittest
+  cancel-in-progress: true
+
+permissions: read-all
+
+jobs:
+  get-default-label-prefix:
+    name: get-default-label-prefix
+    uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
+    if: ${{ (github.event_name != 'schedule' || github.repository == 'pytorch/pytorch') && github.repository_owner == 'pytorch' }}
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
+
+  linux-focal-cuda12_4-py3_10-gcc9-inductor-build:
+    name: cuda12.4-py3.10-gcc9-sm86
+    uses: ./.github/workflows/_linux-build.yml
+    needs: get-default-label-prefix
+    with:
+      runner_prefix: "${{ needs.get-default-label-prefix.outputs.label-type }}"
+      sync-tag: linux-focal-cuda12_4-py3_10-gcc9-inductor-build
+      build-environment: linux-focal-cuda12.4-py3.10-gcc9-sm86
+      docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9-inductor-benchmarks
+      cuda-arch-list: '8.6'
+      test-matrix: |
+        { include: [
+          { config: "inductor", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor_distributed", shard: 1, num_shards: 1, runner: "linux.g5.12xlarge.nvidia.gpu" },
+          { config: "inductor_cpp_wrapper", shard: 1, num_shards: 1, runner: "linux.g5.4xlarge.nvidia.gpu" },
+        ]}
+    secrets:
+      HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+
+  linux-focal-cuda12_4-py3_10-gcc9-inductor-test:
+    name: cuda12.4-py3.10-gcc9-sm86
+    uses: ./.github/workflows/_linux-test.yml
+    needs: linux-focal-cuda12_4-py3_10-gcc9-inductor-build
+    with:
+      sync-tag: linux-focal-cuda12_4-py3_10-gcc9-inductor-test
+      build-environment: linux-focal-cuda12.4-py3.10-gcc9-sm86
+      docker-image: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-inductor-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-inductor-build.outputs.test-matrix }}
+    secrets:
+      HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+
+  linux-focal-cuda12_4-py3_12-gcc9-inductor-build:
+    if: github.repository_owner == 'pytorch'
+    name: cuda12.4-py3.12-gcc9-sm86
+    uses: ./.github/workflows/_linux-build.yml
+    with:
+      build-environment: linux-focal-cuda12.4-py3.12-gcc9-sm86
+      docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3.12-gcc9-inductor-benchmarks
+      cuda-arch-list: '8.6'
+      test-matrix: |
+        { include: [
+          { config: "inductor", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
+          { config: "inductor", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
+        ]}
+
+  linux-focal-cuda12_4-py3_12-gcc9-inductor-test:
+    name: cuda12.4-py3.12-gcc9-sm86
+    uses: ./.github/workflows/_linux-test.yml
+    needs: linux-focal-cuda12_4-py3_12-gcc9-inductor-build
+    with:
+      build-environment: linux-focal-cuda12.4-py3.12-gcc9-sm86
+      docker-image: ${{ needs.linux-focal-cuda12_4-py3_12-gcc9-inductor-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-cuda12_4-py3_12-gcc9-inductor-build.outputs.test-matrix }}
diff --git a/.github/workflows/inductor-cu124.yml b/.github/workflows/inductor-cu124.yml
index 34e8c810a12ccc..63a9bb3edd28e7 100644
--- a/.github/workflows/inductor-cu124.yml
+++ b/.github/workflows/inductor-cu124.yml
@@ -1,3 +1,5 @@
+# Workflow: Inductor
+# runs all inductor cu124 tests, including both benchmark tests and unit tests.
 name: inductor-cu124
 
 on:
@@ -9,7 +11,6 @@ on:
     # Run every 4 hours during the week and every 12 hours on the weekend
     - cron: 45 0,4,8,12,16,20 * * 1-5
     - cron: 45 4,12 * * 0,6
-    - cron: 29 8 * * *  # about 1:29am PDT, for mem leak check and rerun disabled tests
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}
@@ -18,6 +19,11 @@ concurrency:
 permissions: read-all
 
 jobs:
+  unit-test:
+    if: github.repository_owner == 'pytorch'
+    name: inductor-unittest
+    uses: ./.github/workflows/inductor-cu124-unittest.yml
+
   get-default-label-prefix:
     name: get-default-label-prefix
     uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
@@ -40,7 +46,7 @@ jobs:
       check_experiments: "awsa100"
 
   linux-focal-cuda12_4-py3_10-gcc9-inductor-build:
-    # Should be synced with the one in inductor.yml, but this doesn't run inductor_timm
+    # Should be synced with the benchmark tests in inductor.yml, but this doesn't run inductor_timm
     name: cuda12.4-py3.10-gcc9-sm86
     uses: ./.github/workflows/_linux-build.yml
     needs: get-default-label-prefix
@@ -52,9 +58,6 @@ jobs:
       cuda-arch-list: '8.6'
       test-matrix: |
         { include: [
-          { config: "inductor", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_distributed", shard: 1, num_shards: 1, runner: "linux.g5.12xlarge.nvidia.gpu" },
           { config: "inductor_huggingface", shard: 1, num_shards: 1, runner: "linux.g5.4xlarge.nvidia.gpu" },
           { config: "inductor_torchbench", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
           { config: "inductor_torchbench", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
@@ -68,7 +71,6 @@ jobs:
           { config: "aot_inductor_timm", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
           { config: "aot_inductor_torchbench", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
           { config: "aot_inductor_torchbench", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor_cpp_wrapper", shard: 1, num_shards: 1, runner: "linux.g5.4xlarge.nvidia.gpu" },
         ]}
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
@@ -112,26 +114,3 @@ jobs:
       use-gha: anything-non-empty-to-use-gha
     secrets:
       HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-
-  linux-focal-cuda12_4-py3_12-gcc9-inductor-build:
-    if: github.repository_owner == 'pytorch'
-    name: cuda12.4-py3.12-gcc9-sm86
-    uses: ./.github/workflows/_linux-build.yml
-    with:
-      build-environment: linux-focal-cuda12.4-py3.12-gcc9-sm86
-      docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3.12-gcc9-inductor-benchmarks
-      cuda-arch-list: '8.6'
-      test-matrix: |
-        { include: [
-          { config: "inductor", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
-          { config: "inductor", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" },
-        ]}
-
-  linux-focal-cuda12_4-py3_12-gcc9-inductor-test:
-    name: cuda12.4-py3.12-gcc9-sm86
-    uses: ./.github/workflows/_linux-test.yml
-    needs: linux-focal-cuda12_4-py3_12-gcc9-inductor-build
-    with:
-      build-environment: linux-focal-cuda12.4-py3.12-gcc9-sm86
-      docker-image: ${{ needs.linux-focal-cuda12_4-py3_12-gcc9-inductor-build.outputs.docker-image }}
-      test-matrix: ${{ needs.linux-focal-cuda12_4-py3_12-gcc9-inductor-build.outputs.test-matrix }}