From 4bf6c2366818a1eeae257e06ec337039e6895f13 Mon Sep 17 00:00:00 2001
From: "Kevin H. Luu" <khluu000@gmail.com>
Date: Wed, 17 Dec 2025 02:30:56 -0800
Subject: [PATCH] [ci] Sync test areas yaml file with test-pipeline (#30862)

Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
---
 .buildkite/test_areas/e2e_integration.yaml | 19 +------------------
 .buildkite/test_areas/lm_eval.yaml         |  4 ++--
 .buildkite/test_areas/lora.yaml            |  2 ++
 .buildkite/test_areas/models_basic.yaml    |  2 ++
 .buildkite/test_areas/pytorch.yaml         |  4 +++-
 5 files changed, 10 insertions(+), 21 deletions(-)

diff --git a/.buildkite/test_areas/e2e_integration.yaml b/.buildkite/test_areas/e2e_integration.yaml
index 93d389815edac..2e0857986c3fa 100644
--- a/.buildkite/test_areas/e2e_integration.yaml
+++ b/.buildkite/test_areas/e2e_integration.yaml
@@ -32,6 +32,7 @@ steps:
 - label: Prime-RL Integration (2 GPUs)
   timeout_in_minutes: 30
   optional: true
+  soft_fail: true
   num_gpus: 2
   working_dir: "/vllm-workspace"
   source_file_dependencies:
@@ -39,21 +40,3 @@ steps:
   - .buildkite/scripts/run-prime-rl-test.sh
   commands:
     - bash .buildkite/scripts/run-prime-rl-test.sh
-
-- label: DeepSeek V2-Lite Async EPLB Accuracy
-  timeout_in_minutes: 60
-  gpu: h100
-  optional: true
-  num_gpus: 4
-  working_dir: "/vllm-workspace"
-  commands:
-  - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_ep_async_eplb.sh 0.25 1319 8030
-
-- label: Qwen3-Next-80B-A3B-Instruct MTP Async EPLB Accuracy
-  timeout_in_minutes: 60
-  gpu: h100
-  optional: true
-  num_gpus: 4
-  working_dir: "/vllm-workspace"
-  commands:
-  - bash .buildkite/scripts/scheduled_integration_test/qwen3_next_mtp_async_eplb.sh 0.8 1319 8040
diff --git a/.buildkite/test_areas/lm_eval.yaml b/.buildkite/test_areas/lm_eval.yaml
index 9af43e0c375a8..e2498512bdef7 100644
--- a/.buildkite/test_areas/lm_eval.yaml
+++ b/.buildkite/test_areas/lm_eval.yaml
@@ -9,7 +9,7 @@ steps:
   - vllm/model_executor/layers/quantization
   autorun_on_main: true
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
 
 - label: LM Eval Large Models (4 GPUs)(A100)
   gpu: a100
@@ -43,4 +43,4 @@ steps:
   - csrc/
   - vllm/model_executor/layers/quantization
   commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt --tp-size=1
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
diff --git a/.buildkite/test_areas/lora.yaml b/.buildkite/test_areas/lora.yaml
index 809b4138f44ba..59ade40cc8f52 100644
--- a/.buildkite/test_areas/lora.yaml
+++ b/.buildkite/test_areas/lora.yaml
@@ -22,6 +22,8 @@ steps:
     # FIXIT: find out which code initialize cuda before running the test
     # before the fix, we need to use spawn to test it
     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    # Alot of these tests are on the edge of OOMing
+    - export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
     # There is some Tensor Parallelism related processing logic in LoRA that
     # requires multi-GPU testing for validation.
     - pytest -v -s -x lora/test_chatglm3_tp.py
diff --git a/.buildkite/test_areas/models_basic.yaml b/.buildkite/test_areas/models_basic.yaml
index 39a5d51c48833..2a86596a6d603 100644
--- a/.buildkite/test_areas/models_basic.yaml
+++ b/.buildkite/test_areas/models_basic.yaml
@@ -9,6 +9,7 @@ steps:
   source_file_dependencies:
   - vllm/
   - tests/models/test_initialization.py
+  - tests/models/registry.py
   commands:
     # Run a subset of model initialization tests
     - pytest -v -s models/test_initialization.py::test_can_initialize_small_subset
@@ -20,6 +21,7 @@ steps:
   source_file_dependencies:
   - vllm/model_executor/models/
   - tests/models/test_initialization.py
+  - tests/models/registry.py
   commands:
     # Only when vLLM model source is modified - test initialization of a large
     # subset of supported models (the complement of the small subset in the above
diff --git a/.buildkite/test_areas/pytorch.yaml b/.buildkite/test_areas/pytorch.yaml
index 703c82eb1a91b..332d5202d8338 100644
--- a/.buildkite/test_areas/pytorch.yaml
+++ b/.buildkite/test_areas/pytorch.yaml
@@ -13,7 +13,9 @@ steps:
   # tests covered elsewhere.
   # Use `find` to launch multiple instances of pytest so that
   # they do not suffer from https://github.com/vllm-project/vllm/issues/28965
-  - "find compile/ -maxdepth 1 -name 'test_*.py' -exec pytest -s -v {} \\;"
+  # However, find does not normally propagate error codes, so we combine it with xargs
+  # (using -0 for proper path handling)
+  - "find compile/ -maxdepth 1 -name 'test_*.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'"
 
 - label: PyTorch Fullgraph Smoke Test
   timeout_in_minutes: 30