From 8700d68fef855850e2e0aa65056a77b8f80adbdb Mon Sep 17 00:00:00 2001
From: amdfaa <107946068+amdfaa@users.noreply.github.com>
Date: Mon, 20 Oct 2025 16:06:37 +0000
Subject: [PATCH] [ROCm][CI] Update rocm.yml workflow to use 1 GPU ARC runners
 (#165481)

* Moving rocm.yml from using persistent non-ARC runners from the combined MI2xx (MI210 + MI250) cluster to the ARC runners from the MI250 cluster. This halves the number of nodes, but provides access to approximately 4 times the runners, since every 8-GPU MI250 node now provides 8 1-GPU runners. This should help with concurrent capacity and queueing on the MI2xx jobs.

Tested here successfully: https://github.com/pytorch/pytorch/actions/runs/18620814622/job/53092469720

Pull Request resolved: https://github.com/pytorch/pytorch/pull/165481
Approved by: https://github.com/jeffdaily, https://github.com/pruthvistony, https://github.com/albanD

Co-authored-by: Jithun Nair <37884920+jithunnair-amd@users.noreply.github.com>
---
 .github/actionlint.yaml    | 13 +++++++++----
 .github/workflows/rocm.yml | 12 ++++++------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/.github/actionlint.yaml b/.github/actionlint.yaml
index d021371ca88..3a3d2a2e699 100644
--- a/.github/actionlint.yaml
+++ b/.github/actionlint.yaml
@@ -1,4 +1,4 @@
-self-hosted-runner:
+runnerssted-runner:
   labels:
     # GitHub hosted runner that actionlint doesn't recognize because actionlint version (1.6.21) is too old
     - ubuntu-24.04
@@ -54,12 +54,17 @@ self-hosted-runner:
     - windows-11-arm64
     - windows-11-arm64-preview
     # Organization-wide AMD-hosted runners
-    # MI2xx runners
+    # MI2xx non-ARC runners
     - linux.rocm.gpu
-    - linux.rocm.gpu.mi250
     - linux.rocm.gpu.2
     - linux.rocm.gpu.4
-    # gfx942 runners
+    - linux.rocm.gpu.mi250
+    - linux.rocm.gpu.gfx1100
+    # MI2xx ARC runners
+    - linux.rocm.gpu.mi250.1
+    - linux.rocm.gpu.mi250.2
+    - linux.rocm.gpu.mi250.4
+    # gfx942 ARC runners
     - linux.rocm.gpu.gfx942.1
     - linux.rocm.gpu.gfx942.2
     - linux.rocm.gpu.gfx942.4
diff --git a/.github/workflows/rocm.yml b/.github/workflows/rocm.yml
index e6bc43f34f8..36cc5fd0e8e 100644
--- a/.github/workflows/rocm.yml
+++ b/.github/workflows/rocm.yml
@@ -36,12 +36,12 @@ jobs:
       sync-tag: rocm-build
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 6, runner: "linux.rocm.gpu.2" },
-          { config: "default", shard: 2, num_shards: 6, runner: "linux.rocm.gpu.2" },
-          { config: "default", shard: 3, num_shards: 6, runner: "linux.rocm.gpu.2" },
-          { config: "default", shard: 4, num_shards: 6, runner: "linux.rocm.gpu.2" },
-          { config: "default", shard: 5, num_shards: 6, runner: "linux.rocm.gpu.2" },
-          { config: "default", shard: 6, num_shards: 6, runner: "linux.rocm.gpu.2" },
+          { config: "default", shard: 1, num_shards: 6, runner: "linux.rocm.gpu.mi250.1" },
+          { config: "default", shard: 2, num_shards: 6, runner: "linux.rocm.gpu.mi250.1" },
+          { config: "default", shard: 3, num_shards: 6, runner: "linux.rocm.gpu.mi250.1" },
+          { config: "default", shard: 4, num_shards: 6, runner: "linux.rocm.gpu.mi250.1" },
+          { config: "default", shard: 5, num_shards: 6, runner: "linux.rocm.gpu.mi250.1" },
+          { config: "default", shard: 6, num_shards: 6, runner: "linux.rocm.gpu.mi250.1" },
         ]}
     secrets: inherit