Run iPhone benchmark on private devices

.ci/scripts/gather_benchmark_configs.py

@@ -24,6 +24,7 @@
     "samsung_galaxy_s24": "arn:aws:devicefarm:us-west-2:308535385114:devicepool:02a2cf0f-6d9b-45ee-ba1a-a086587469e6/98f8788c-2e25-4a3c-8bb2-0d1e8897c0db",
     "google_pixel_8_pro": "arn:aws:devicefarm:us-west-2:308535385114:devicepool:02a2cf0f-6d9b-45ee-ba1a-a086587469e6/d65096ab-900b-4521-be8b-a3619b69236a",
     "google_pixel_3_private_rooted": "arn:aws:devicefarm:us-west-2:308535385114:devicepool:02a2cf0f-6d9b-45ee-ba1a-a086587469e6/98d23ca8-ea9e-4fb7-b725-d402017b198d",
+    "apple_iphone_15_private": "arn:aws:devicefarm:us-west-2:308535385114:devicepool:02a2cf0f-6d9b-45ee-ba1a-a086587469e6/55929353-2f28-4ee5-bdff-d1a95f58cb28",
 }
 
 # Predefined benchmark configurations

.github/workflows/apple-perf-private-device-experiment.yml

@@ -0,0 +1,64 @@
+name: apple-perf (private devices)
+
+on:
+  # TODO (huydhn): Disable the schedule run until we land the change to add device pool and device name
+  # to separate between public and private iOS devices
+  # schedule:
+  # - cron: 0 0,4,8,12,16,20 * * *
+  pull_request:
+    paths:
+      - .github/workflows/apple-perf-private-device-experiment.yml
+  # push:
+  #   branches:
+  #     - main
+  #   paths:
+  #     - .github/workflows/apple-perf-private-device-experiment.yml
+  # Note: GitHub has an upper limit of 10 inputs
+  workflow_dispatch:
+    inputs:
+      models:
+        description: Models to be benchmarked
+        required: false
+        type: string
+        default: mv3,meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8,meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8
+      devices:
+        description: Target devices to run benchmark
+        required: false
+        type: string
+        default: apple_iphone_15_private
+      benchmark_configs:
+        description: The list of configs used the benchmark
+        required: false
+        type: string
+  workflow_call:
+    inputs:
+      models:
+        description: Models to be benchmarked
+        required: false
+        type: string
+        default: mv3,meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8,meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8
+      devices:
+        description: Target devices to run benchmark
+        required: false
+        type: string
+        default: apple_iphone_15_private
+      benchmark_configs:
+        description: The list of configs used the benchmark
+        required: false
+        type: string
+
+concurrency:
+  group: apple-perf-private-devices-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
+  cancel-in-progress: true
+
+jobs:
+  apple:
+    uses: ./.github/workflows/apple-perf.yml
+    secrets: inherit
+    permissions:
+      id-token: write
+      contents: read
+    with:
+      models: ${{ inputs.models || 'mv3,meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8,meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8' }}
+      devices: apple_iphone_15_private
+      benchmark_configs: ${{ inputs.benchmark_configs }}