From 4e4eab73ed2b4e00931a4636e926b8df1cb1fe50 Mon Sep 17 00:00:00 2001 From: "Kevin H. Luu" Date: Mon, 12 Oct 2026 23:57:32 -0700 Subject: [PATCH] [CI] Shard Model Executor and L4 Pipeline + Context Parallelism automatically (#61202) Signed-off-by: khluu Co-authored-by: Claude Opus 5.5 --- .buildkite/test_areas/distributed.yaml | 1 + .buildkite/test_areas/model_executor.yaml | 1 + 2 files changed, 2 insertions(+) diff --git a/.buildkite/test_areas/distributed.yaml b/.buildkite/test_areas/distributed.yaml index b30cbac0ce..2f929b53b8 100644 --- a/.buildkite/test_areas/distributed.yaml +++ b/.buildkite/test_areas/distributed.yaml @@ -641,6 +641,7 @@ steps: - label: ":nvidia: (L4) Pipeline + Context Parallelism" key: pipeline-context-parallelism-4-gpus + automatic_shard: true timeout_in_minutes: 55 working_dir: "/vllm-workspace/tests" device: l4 diff --git a/.buildkite/test_areas/model_executor.yaml b/.buildkite/test_areas/model_executor.yaml index a23359b768..c9f467941a 100644 --- a/.buildkite/test_areas/model_executor.yaml +++ b/.buildkite/test_areas/model_executor.yaml @@ -5,6 +5,7 @@ steps: - label: ":nvidia: (H200 MIG 35GB) Model Executor" device: h200_35gb key: model-executor + automatic_shard: true timeout_in_minutes: 60 source_file_dependencies: - vllm/engine/arg_utils.py