From 50c111d328c4fad21cd30a22972a6ad12bbfef55 Mon Sep 17 00:00:00 2001 From: Akash Verma Date: Wed, 15 Apr 2026 11:26:36 -0500 Subject: [PATCH 1/2] Increased the timeout for features test to 60 minutes. --- .github/workflows/integration_test_8gpu_features.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/integration_test_8gpu_features.yaml b/.github/workflows/integration_test_8gpu_features.yaml index 86a3d5c0f3..2688d5f692 100644 --- a/.github/workflows/integration_test_8gpu_features.yaml +++ b/.github/workflows/integration_test_8gpu_features.yaml @@ -46,7 +46,7 @@ jobs: docker-image: ${{ matrix.docker-image }} repository: pytorch/torchtitan upload-artifact: outputs - timeout: 45 + timeout: 60 script: | set -eux From 51c0c5e71c7c769449612ef882b817d6f5f1714e Mon Sep 17 00:00:00 2001 From: Akash Verma Date: Thu, 16 Apr 2026 19:30:28 -0500 Subject: [PATCH 2/2] Made timeout rocm specific. --- .github/workflows/integration_test_8gpu_features.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/integration_test_8gpu_features.yaml b/.github/workflows/integration_test_8gpu_features.yaml index 2688d5f692..39a19c6e61 100644 --- a/.github/workflows/integration_test_8gpu_features.yaml +++ b/.github/workflows/integration_test_8gpu_features.yaml @@ -46,7 +46,7 @@ jobs: docker-image: ${{ matrix.docker-image }} repository: pytorch/torchtitan upload-artifact: outputs - timeout: 60 + timeout: ${{ matrix.gpu-arch-type == 'rocm' && 60 || 45 }} # TODO: change it to 45min when MI350 label is added. script: | set -eux