From 59a095869bd9c13852ba24058b196da323bcb3ac Mon Sep 17 00:00:00 2001 From: Leo Fang Date: Mon, 5 Oct 2026 23:07:36 -0400 Subject: [PATCH] Revert "ci: temporarily pause GB300 nightly run (#2941)" This reverts commit c7028166d742b589b02e9962040f5a9c00c176a7. --- ci/test-matrix.yml | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/ci/test-matrix.yml b/ci/test-matrix.yml index df0b9600492..bd67db94ff2 100644 --- a/ci/test-matrix.yml +++ b/ci/test-matrix.yml @@ -111,8 +111,7 @@ linux: - { ARCH: 'amd64', PY_VER: '3.12', CUDA_VER: '13.4.2', LOCAL_CTK: '0', GPU: 'a100', GPU_COUNT: '1', DRIVER: 'latest', ENV: { MODE: 'nightly-cuda-core' } } # nightly-standard (arm64 nightly-only runners — per runner team request) - { ARCH: 'arm64', PY_VER: '3.13', CUDA_VER: '13.4.2', LOCAL_CTK: '1', GPU: 'gh200', GPU_COUNT: '1', DRIVER: 'latest', ENV: { MODE: 'nightly-standard' } } - # GB300 paused until runner thermal issues are resolved (NVBugs 6393185). - # - { ARCH: 'arm64', PY_VER: '3.14', CUDA_VER: '13.4.2', LOCAL_CTK: '1', GPU: 'gb300', GPU_COUNT: '1', DRIVER: 'latest', ENV: { MODE: 'nightly-standard' } } + - { ARCH: 'arm64', PY_VER: '3.14', CUDA_VER: '13.4.2', LOCAL_CTK: '1', GPU: 'gb300', GPU_COUNT: '1', DRIVER: 'latest', ENV: { MODE: 'nightly-standard' } } - { ARCH: 'arm64', PY_VER: '3.14', CUDA_VER: '13.4.2', LOCAL_CTK: '1', GPU: 'l4', GPU_COUNT: '2', DRIVER: 'latest', ENV: { MODE: 'nightly-standard' } } - { ARCH: 'arm64', PY_VER: '3.14t', CUDA_VER: '13.4.2', LOCAL_CTK: '1', GPU: 'l4', GPU_COUNT: '2', DRIVER: 'latest', ENV: { MODE: 'nightly-standard' } } # amd64 with h200 (nightly-only, as there is only one server with h200s)