[CI] Recalibrate rebase-raised timeouts on post-merge nightly durations

Only post-#4709 nightlies (#2474/#2486, both on rebased code) are a valid
baseline; the rebase changed step runtimes substantially. Revert the raises
that post-merge data no longer supports and keep the ones it confirms:

- Omni Function H100: keep 120m (post-merge 59-71 min vs old 90m ceiling)
- Omni Perf No Async Chunk: 300m -> 180m (post-merge 41-44 min)
- TTS Function L4: 120m -> 90m (post-merge ~27 min)
- Diffusion X2I L4: 120m -> 60m (post-merge ~18 min)
- IndexTTS2: 60m/45m -> 40m/35m (steady ~12.5 min warm, cold kill at 20.7m)
- CustomVoice/Base 40m and Qwen3-Omni 50m: keep (9-21 min warm + cold-cache
  headroom the old limits lacked)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

.buildkite/test-merge.yml

@@ -173,9 +173,9 @@ steps:
           - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
           - vllm_omni/deploy/qwen3_tts.yaml
         commands:
-          # 40m (was 20m): nightly history shows passing runs at ~9-12 min, but
-          # cold-cache runs were killed by the 20m limit (e.g. nightly #2444
-          # died at 25.2m wall), masking the real failure output.
+          # 40m (was 20m): post-rebase runs take 9-12 min warm, but cold-cache
+          # runs exceed 20m and were killed without failure output (a cold run
+          # died at 25.2m wall under the old limit).
           - |
             timeout 40m bash -c "
               export VLLM_LOGGING_LEVEL=DEBUG
@@ -203,9 +203,9 @@ steps:
           - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
           - vllm_omni/deploy/qwen3_tts.yaml
         commands:
-          # 40m (was 20m): nightly history shows passing runs at ~9-13 min, but
-          # cold-cache runs were killed by the 20m limit (e.g. nightly #2444
-          # died at 25.2m wall), masking the real failure output.
+          # 40m (was 20m): post-rebase runs take 9-13 min warm, but cold-cache
+          # runs exceed 20m and were killed without failure output (a cold run
+          # died at 25.2m wall under the old limit).
           - |
             timeout 40m bash -c "
               export VLLM_LOGGING_LEVEL=DEBUG
@@ -268,13 +268,13 @@ steps:
           - vllm_omni/entrypoints/openai/tts_adapters/indextts2.py
           - vllm_omni/config/pipeline_registry.py
           - vllm_omni/model_executor/models/registry.py
-        # 60m/45m (was 20m/20m): warm runs take a steady ~12.5 min, but the old
-        # 20m limit killed a cold run at 20.7m (nightly #2444, timed_out) with
-        # no failure output.
-        timeout_in_minutes: 60
+        # 40m/35m (was 20m/20m): post-rebase runs take a steady ~12.5 min warm,
+        # but a cold run was killed at 20.7m under the old limit with no
+        # failure output; the rebase-time raise to 60m/45m was oversized.
+        timeout_in_minutes: 40
         commands:
           - |
-            timeout 45m bash -c "
+            timeout 35m bash -c "
               export VLLM_LOGGING_LEVEL=DEBUG
               pytest -s -v tests/e2e/online_serving/test_indextts2.py tests/e2e/offline_inference/test_indextts2.py -m 'advanced_model and cuda' --run-level 'advanced_model'
             "
@@ -299,8 +299,8 @@ steps:
           - vllm_omni/model_executor/models/qwen3_omni/
           - vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
           - vllm_omni/deploy/qwen3_omni_moe.yaml
-        # 50m (was 30m): nightly history shows warm runs at 15-21 min; 30m left
-        # no headroom for cold-cache runs, which were killed without output.
+        # 50m (was 30m): post-rebase runs take 15-21 min warm; 30m left no
+        # headroom for cold-cache runs, which were killed without output.
         timeout_in_minutes: 50
         commands:
           - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py -m 'advanced_model and cuda' --run-level 'advanced_model'

.buildkite/test-nightly.yml

@@ -12,8 +12,9 @@ steps:
     if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "omni-test"
     steps:
       - label: ":full_moon: Omni · Function Test with H100"
-        # 120m (was 90m): nightly runs take 55-70 min, and #2444 (2026-06-29)
-        # still hit the old 90m ceiling (timed_out at 90.8m) with no output.
+        # 120m (was 90m): post-rebase nightlies (#2474/#2486) run 59-71 min —
+        # too close to the old 90m ceiling, which #2444 already hit (killed at
+        # 90.8m with no failure output).
         timeout_in_minutes: 120
         commands:
           - pytest -sv tests/e2e --run-level "full_model" -m "full_model and H100 and omni" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_qwen3_omni_multi_replicas.py
@@ -155,10 +156,10 @@ steps:
 
       - label: ":full_moon: Omni · Perf Test · No Async Chunk"
         key: nightly-omni-performance-no-async-chunk
-        # 300m (was 180m): typically 35-44 min, but slow nights blow up badly —
-        # nightly #2444 (2026-06-29) passed at 179.4m, a hair under the old
-        # 180m limit; killing such a run would mask the perf result entirely.
-        timeout_in_minutes: 300
+        # 180m: post-rebase nightlies (#2474/#2486) run 41-44 min; the
+        # rebase-time raise to 300m targeted a pre-rebase 179.4m outlier and
+        # is no longer needed.
+        timeout_in_minutes: 180
         commands:
           - export BENCHMARK_DIR=tests/dfx/perf/results
           - |
@@ -381,9 +382,10 @@ steps:
     if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "tts-test"
     steps:
       - label: ":full_moon: TTS · Function Test with L4"
-        # 120m (was 90m): passing nightly runs took 72-87 min under the old
-        # 90m limit (2026-06-23 pass at 86.9m) — effectively zero headroom.
-        timeout_in_minutes: 120
+        # 90m: post-rebase nightlies (#2474/#2486) run ~27 min; the rebase-time
+        # raise to 120m targeted pre-rebase 72-87 min runs and is no longer
+        # needed.
+        timeout_in_minutes: 90
         commands:
           - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
           - export VLLM_USE_DEEP_GEMM="0"
@@ -833,10 +835,10 @@ steps:
 
 
       - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with L4"
-        # 120m (was 60m): nightly runs took 48-58 min under the old 60m limit
-        # (near-zero headroom) until 2026-06-29; ~18 min since. Revisit if the
-        # step stays at the lighter weight.
-        timeout_in_minutes: 120
+        # 60m: post-rebase nightlies (#2474/#2486) run ~18 min; the rebase-time
+        # raise to 120m targeted pre-rebase 48-58 min runs and is no longer
+        # needed.
+        timeout_in_minutes: 60
         commands:
           - pytest -sv tests/e2e/ -k "not test_wan and not test_bagel_expansion and not hunyuan" -m "full_model and diffusion and L4" --run-level "full_model" --ignore=tests/e2e/accuracy
         agents: