[CI][Bugfix] Update environment variables for test configurations in Buildkite YAML files to resolve HF timeout (vllm-project#2628)

Signed-off-by: wangyu <410167048@qq.com>

Author: yenuo26

.buildkite/test-merge.yml

@@ -1,3 +1,8 @@
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
 steps:
   - label: "Simple Unit Test"
     depends_on: upload-merge-pipeline
@@ -169,7 +174,6 @@ steps:
     commands:
       - |
         timeout 15m bash -c '
-                export VLLM_WORKER_MULTIPROC_METHOD=spawn
                 pytest -s -v tests/engine/test_async_omni_engine_abort.py
         '
     agents:
@@ -191,7 +195,6 @@ steps:
     depends_on: upload-merge-pipeline
     commands:
       - export VLLM_LOGGING_LEVEL=DEBUG
-      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
       - pytest -s -v tests/e2e/offline_inference/test_qwen2_5_omni.py tests/e2e/online_serving/test_qwen2_5_omni.py -m "advanced_model" --run-level "advanced_model"
     agents:
       queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
@@ -212,7 +215,6 @@ steps:
       - |
         timeout 20m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
           pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py tests/e2e/offline_inference/test_qwen3_tts_customvoice.py -m "advanced_model" --run-level "advanced_model"
         '
@@ -235,7 +237,6 @@ steps:
       - |
         timeout 20m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
           pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m "advanced_model" --run-level "advanced_model"
         '
@@ -256,7 +257,6 @@ steps:
     timeout_in_minutes: 30
     depends_on: upload-merge-pipeline
     commands:
-      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
       - export VLLM_TEST_CLEAN_GPU_MEMORY="1"
       - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py tests/e2e/online_serving/test_mimo_audio.py -m "advanced_model" --run-level "advanced_model"
     agents:
@@ -297,7 +297,6 @@ steps:
     timeout_in_minutes: 20
     depends_on: upload-merge-pipeline
     commands:
-      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
       - pytest -s -v tests/e2e/online_serving/test_image_gen_edit.py
     agents:
       queue: "mithril-h100-pool"
@@ -340,7 +339,6 @@ steps:
       - |
         timeout 55m bash -c '
           set -e
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           export VLLM_TEST_CLEAN_GPU_MEMORY=1
           export VLLM_IMAGE_FETCH_TIMEOUT=60
           pytest -s -v tests/e2e/offline_inference/test_bagel_text2img.py -m "advanced_model" --run-level "advanced_model" -k "shared_memory"
@@ -387,7 +385,6 @@ steps:
       - |
         timeout 20m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           pytest -s -v tests/e2e/online_serving/test_voxtral_tts.py tests/e2e/offline_inference/test_voxtral_tts.py -m "advanced_model" --run-level "advanced_model"
         '
     agents:

.buildkite/test-nightly-diffusion.yml

@@ -2,6 +2,11 @@
 #   buildkite-agent pipeline upload .buildkite/test-nightly-diffusion.yml
 # from test-nightly.yml (step key: nightly-diffusion-model-test). Top-level groups are
 # foldable in the Buildkite UI (Other / Wan / Qwen-Image).
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
 steps:
   - group: ":card_index_dividers: Other Model Test"
     key: nightly-other-model-test-group
@@ -10,7 +15,6 @@ steps:
         timeout_in_minutes: 120
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/online_serving/test_*_expansion.py -k "not test_wan22_expansion and not test_wan_2_1_vace_expansion and not test_qwen_image" -m "advanced_model and diffusion and H100" --run-level "advanced_model"
         agents:
           queue: "mithril-h100-pool"
@@ -50,7 +54,6 @@ steps:
         timeout_in_minutes: 60
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/online_serving/test_*_expansion.py -m "advanced_model and diffusion and L4" --run-level "advanced_model"
         agents:
           queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
@@ -70,7 +73,6 @@ steps:
         timeout_in_minutes: 60
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - export VLLM_TEST_CLEAN_GPU_MEMORY="1"
           - pytest -s -v tests/examples/online_serving/test_text_to_image.py tests/examples/offline_inference/test_text_to_image.py -m "advanced_model and example and H100" --run-level "advanced_model"
         agents:
@@ -114,7 +116,6 @@ steps:
         timeout_in_minutes: 90
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py tests/e2e/online_serving/test_wan_2_1_vace_expansion.py -m "advanced_model" --run-level "advanced_model"
         agents:
           queue: "mithril-h100-pool"
@@ -155,7 +156,6 @@ steps:
         timeout_in_minutes: 180
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/accuracy/wan22_i2v/test_wan22_i2v_video_similarity.py --run-level advanced_model
         agents:
           queue: "mithril-h100-pool"
@@ -198,7 +198,6 @@ steps:
         timeout_in_minutes: 120
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/online_serving/test_qwen_image*_expansion.py -m "advanced_model and diffusion and H100" --run-level "advanced_model"
         agents:
           queue: "mithril-h100-pool"
@@ -239,7 +238,6 @@ steps:
         timeout_in_minutes: 60
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/accuracy/test_gebench_h100_smoke.py --run-level advanced_model --gebench-model Qwen/Qwen-Image-2512 --accuracy-judge-model QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQ --accuracy-gpu 0 --gebench-port 8093 --accuracy-workers 1
           - buildkite-agent artifact upload "tests/e2e/accuracy/artifacts/gebench_qwen-image-2512/summary*.json"
         agents:
@@ -281,7 +279,6 @@ steps:
         timeout_in_minutes: 60
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/accuracy/test_gedit_bench_h100_smoke.py --run-level advanced_model --gedit-model Qwen/Qwen-Image-Edit --accuracy-judge-model QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQ --accuracy-gpu 0 --gedit-port 8093 --gedit-samples-per-group 20 --accuracy-workers 1
           - buildkite-agent artifact upload "tests/e2e/accuracy/artifacts/gedit_scores_qwen-image-edit/qwen-image-edit_all_all_vie_score_*.csv"
           - buildkite-agent artifact upload "tests/e2e/accuracy/artifacts/gedit_scores_qwen-image-edit/qwen-image-edit_all_all_summary_*.json"
@@ -326,7 +323,6 @@ steps:
         timeout_in_minutes: 180
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
           - export CACHE_DIT_VERSION=1.3.0
           - pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --config-file tests/dfx/perf/tests/test_qwen_image_vllm_omni.json

.buildkite/test-nightly.yml

@@ -1,3 +1,8 @@
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
 steps:
   # Group: collapses under one heading in the Buildkite UI; child steps still run in parallel.
   - group: ":card_index_dividers: Omni Model Test"
@@ -8,7 +13,6 @@ steps:
         depends_on: upload-nightly-pipeline
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/e2e/online_serving/test_*_expansion.py -m "advanced_model and H100 and omni" --run-level "advanced_model"
         agents:
           queue: "mithril-h100-pool"
@@ -49,7 +53,6 @@ steps:
         depends_on: upload-nightly-pipeline
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
           - pytest -s -v tests/e2e/online_serving/test_*_expansion.py -m "advanced_model and L4 and omni" --run-level "advanced_model"
         agents:
@@ -71,7 +74,6 @@ steps:
         depends_on: upload-nightly-pipeline
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
           - pytest -s -v tests/examples/ -m "advanced_model and omni and L4" --run-level "advanced_model"
         agents:
@@ -93,7 +95,6 @@ steps:
         depends_on: upload-nightly-pipeline
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - pytest -s -v tests/examples/ -m "advanced_model and omni and H100" --run-level "advanced_model"
         agents:
           queue: "mithril-h100-pool"
@@ -135,7 +136,6 @@ steps:
         depends_on: upload-nightly-pipeline
         if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
         commands:
-          - export VLLM_WORKER_MULTIPROC_METHOD=spawn
           - export BENCHMARK_DIR=tests/dfx/perf/results
           - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
           - pytest -s -v tests/dfx/perf/scripts/run_benchmark.py
@@ -193,7 +193,6 @@ steps:
     depends_on: upload-nightly-pipeline
     if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
     commands:
-      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
       - python tools/nightly/buildkite_testcase_statistics.py -o tests/dfx/perf/results/buildkite_testcase_statistics.html
       - buildkite-agent artifact upload "tests/dfx/perf/results/*.html"
     agents:

.buildkite/test-ready.yml

@@ -1,3 +1,8 @@
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
 steps:
   - label: "Simple Unit Test"
     depends_on: upload-ready-pipeline
@@ -173,7 +178,6 @@ steps:
     commands:
       - |
         timeout 15m bash -c '
-                export VLLM_WORKER_MULTIPROC_METHOD=spawn
                 pytest -s -v tests/engine/test_async_omni_engine_abort.py
         '
     agents:
@@ -197,7 +201,6 @@ steps:
       - |
         timeout 17m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           pytest -s -v tests/e2e/online_serving/test_qwen2_5_omni.py -m "core_model" --run-level "core_model"
         '
     agents:
@@ -218,7 +221,6 @@ steps:
     commands:
       - |
         timeout 20m bash -c '
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
         '
     agents:
@@ -256,7 +258,6 @@ steps:
       - |
         timeout 30m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           pytest -s -v tests/e2e/online_serving/test_mimo_audio.py -m "core_model" --run-level "core_model"
         '
     agents:
@@ -299,7 +300,6 @@ steps:
       - |
         timeout 20m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
           pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m "core_model" --run-level "core_model"
         '
@@ -324,7 +324,6 @@ steps:
       - |
         timeout 20m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           pytest -s -v tests/e2e/online_serving/test_omnivoice.py -m "core_model" --run-level "core_model"
         '
     agents:
@@ -347,7 +346,6 @@ steps:
       - |
         timeout 20m bash -c '
           export VLLM_LOGGING_LEVEL=DEBUG
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           pytest -s -v tests/e2e/online_serving/test_voxtral_tts.py -m "core_model" --run-level "core_model"
         '
     agents:
@@ -384,7 +382,6 @@ steps:
   #   commands:
   #     - |
   #       timeout 20m bash -c '
-  #         export VLLM_WORKER_MULTIPROC_METHOD=spawn
   #         pytest -s -v tests/e2e/online_serving/test_image_gen_edit.py
   #       '
   #   agents:
@@ -421,7 +418,6 @@ steps:
     commands:
       - |
         timeout 30m bash -c '
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           export VLLM_TEST_CLEAN_GPU_MEMORY=1
           pytest -s -v tests/e2e/offline_inference/test_bagel_text2img.py -m "core_model" --run-level "core_model"
         '
@@ -464,7 +460,6 @@ steps:
     commands:
       - |
         timeout 30m bash -c '
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           export VLLM_TEST_CLEAN_GPU_MEMORY=1
           pytest -s -v tests/e2e/offline_inference/test_bagel_img2img.py -m "core_model" --run-level "core_model"
         '
@@ -507,7 +502,6 @@ steps:
     commands:
       - |
         timeout 40m bash -c '
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           export VLLM_TEST_CLEAN_GPU_MEMORY=1
           export VLLM_IMAGE_FETCH_TIMEOUT=60
           pytest -s -v tests/e2e/online_serving/test_bagel_online.py -m "core_model" --run-level "core_model"
@@ -552,7 +546,6 @@ steps:
     commands:
       - |
         timeout 20m bash -c '
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
           pytest -s -v tests/e2e/online_serving/test_cosyvoice3_tts.py -m "core_model" --run-level "core_model"
         '
     agents: