[CI/Build] Add experimental AMD MI300 nightly lane (#6978)

Signed-off-by: andyluo7 <andy.luo@amd.com>

.buildkite/amd/scripts/bootstrap-amd-omni.sh

@@ -60,7 +60,8 @@ resolve_test_specs() {
     if ! selected_specs=$(python3 "$AMD_SUITE_SELECTOR" \
         --branch "$BUILDKITE_BRANCH" \
         --labels "$PR_LABELS" \
-        --debug-test-yaml "${DEBUG_TEST_YAML:-}"); then
+        --debug-test-yaml "${DEBUG_TEST_YAML:-}" \
+        --nightly "$NIGHTLY"); then
         exit 1
     fi
 
@@ -80,6 +81,12 @@ filter_test_specs_by_skip_ci() {
         case "$suite_spec" in
             READY_TESTS:*) level="l2" ;;
             MERGE_TESTS:*) level="l3" ;;
+            NIGHTLY_TESTS:*)
+                # Explicit PR and scheduled nightly selections must survive
+                # L2/L3 diff gating, including docs-only main commits.
+                runnable_specs+=("$suite_spec")
+                continue
+                ;;
             *)
                 echo "ERROR: unknown AMD test suite spec '$suite_spec'" >&2
                 exit 1
@@ -101,7 +108,7 @@ filter_test_specs_by_skip_ci() {
                 ":memo: CI skipped — docs or pytest skip-mark changes only" \
                 --style "info" 2>/dev/null || true
         fi
-        echo "No AMD L2/L3 suites remain after skip-ci filtering."
+        echo "No AMD suites remain after skip-ci filtering."
         exit 0
     fi
 }
@@ -219,8 +226,8 @@ if [[ $BUILDKITE_BRANCH == "main" ]]; then
     file_diff=$(get_diff_main)
 fi
 
-# Resolve PR tier labels before skip-ci so ready and merge suites can be
-# filtered independently for CI-YAML-only changes.
+# Resolve PR tier labels before skip-ci so ready/merge suites can be filtered
+# independently while an explicitly selected nightly suite passes through.
 resolve_test_specs
 filter_test_specs_by_skip_ci
 

.buildkite/amd/scripts/select_test_suites.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
-"""Select AMD L2/L3 suites after Buildkite has created an AMD build.
+"""Select AMD ready/merge/nightly suites after Buildkite creates a build.
 
 This repository-side selector does not decide which GitHub label events start
 the external ``vllm-omni-amd-ci`` pipeline. Its Buildkite PR build condition
@@ -17,6 +17,7 @@ from collections.abc import Iterable
 SUITE_SPECS = {
     "ready": "READY_TESTS:test-amd-ready.yml",
     "merge": "MERGE_TESTS:test-amd-merge.yml",
+    "nightly": "NIGHTLY_TESTS:test-amd-nightly.yml",
 }
 
 
@@ -28,7 +29,7 @@ def _parse_debug_suites(value: str) -> tuple[str, ...]:
     seen: set[str] = set()
     for suite in suites:
         if suite not in SUITE_SPECS:
-            raise ValueError(f"DEBUG_TEST_YAML entries must be 'merge' or 'ready', got {suite!r}")
+            raise ValueError(f"DEBUG_TEST_YAML entries must be 'merge', 'nightly', or 'ready', got {suite!r}")
         if suite in seen:
             raise ValueError(f"duplicate DEBUG_TEST_YAML suite {suite!r}")
         seen.add(suite)
@@ -40,18 +41,27 @@ def select_amd_test_suites(
     branch: str,
     labels: Iterable[str],
     debug_test_yaml: str = "",
+    nightly: bool = False,
 ) -> tuple[str, ...]:
     """Return ordered suite names while preserving legacy unlabeled PRs."""
 
     if debug_test_yaml:
         return _parse_debug_suites(debug_test_yaml)
     if branch == "main":
-        return ("merge",)
+        return ("nightly",) if nightly else ("merge",)
 
     label_set = {label.strip() for label in labels if label.strip()}
-    selected = tuple(suite for label, suite in (("ready", "ready"), ("merge-test", "merge")) if label in label_set)
-    # AMD historically uploaded L2 for every PR build. Keep that behavior for
-    # triggers such as amd-test while adding tier selection for ready/merge-test.
+    selected = tuple(
+        suite
+        for label, suite in (
+            ("ready", "ready"),
+            ("merge-test", "merge"),
+            ("nightly-test", "nightly"),
+        )
+        if label in label_set
+    )
+    # AMD historically uploaded the ready suite for every admitted PR build.
+    # Preserve that fallback when no explicit tier label is present.
     return selected or ("ready",)
 
 
@@ -60,6 +70,7 @@ def main() -> int:
     parser.add_argument("--branch", required=True)
     parser.add_argument("--labels", default="")
     parser.add_argument("--debug-test-yaml", default="")
+    parser.add_argument("--nightly", type=int, choices=(0, 1), default=0)
     args = parser.parse_args()
 
     labels = tuple(args.labels.splitlines())
@@ -68,19 +79,15 @@ def main() -> int:
             branch=args.branch,
             labels=labels,
             debug_test_yaml=args.debug_test_yaml,
+            nightly=bool(args.nightly),
         )
     except ValueError as exc:
         parser.error(str(exc))
 
     label_set = {label.strip() for label in labels if label.strip()}
-    if not args.debug_test_yaml and args.branch != "main" and not ({"ready", "merge-test"} & label_set):
+    if args.branch != "main" and not args.debug_test_yaml and not ({"ready", "merge-test", "nightly-test"} & label_set):
         print(
-            "No AMD L2/L3 tier label found; preserving the legacy ready-suite fallback.",
-            file=sys.stderr,
-        )
-    if "nightly-test" in label_set:
-        print(
-            "AMD nightly-test has no suite yet and does not affect L2/L3 selection.",
+            "No AMD ready/merge/nightly label found; preserving the legacy ready-suite fallback.",
             file=sys.stderr,
         )
 

.buildkite/amd/test-amd-nightly.yml

@@ -0,0 +1,66 @@
+# AMD MI300 `full_model` nightly coverage during burn-in.
+# All jobs are non-blocking until the lane has stable runtime evidence.
+# Historical build #11646 was red in Function Expansion and Accuracy (one
+# async_chunk similarity mismatch; Seed-TTS WER 0.376480 > 0.35).
+
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
+steps:
+  # MI325 is the repository's legacy ROCm pytest marker. The AMD template maps
+  # agent_pool to the current MI300 Buildkite queues independently of that mark.
+  - group: ":full_moon: Qwen3-Omni MI300 Nightly"
+    steps:
+      - label: "Qwen3-Omni Function Expansion"
+        agent_pool: mi300_2
+        depends_on: amd-build
+        mirror_hardwares: [amdproduction]
+        grade: NonBlocking
+        timeout_in_minutes: 180
+        commands:
+          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
+          - pytest -s -v tests/e2e/online_serving/test_qwen3_omni_expansion.py -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"
+
+      - label: "Qwen3-Omni Accuracy"
+        agent_pool: mi300_2
+        depends_on: amd-build
+        mirror_hardwares: [amdproduction]
+        grade: NonBlocking
+        timeout_in_minutes: 180
+        artifact_paths:
+          - tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc/*.json
+        commands:
+          - export SEED_TTS_WER_EVAL=1
+          # PyTorch ROCm uses the torch.cuda device namespace.
+          - export SEED_TTS_EVAL_DEVICE=cuda:1
+          - pytest -s -v tests/e2e/accuracy/qwen3_omni/test_qwen3_omni.py -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"
+          # Native tests run from the image copy under /app/vllm-omni, while
+          # Buildkite's artifact hook searches the checkout workspace.
+          - |
+            if [[ "$$PWD" != "$${BUILDKITE_BUILD_CHECKOUT_PATH:?}" ]]; then
+              artifact_dir="$${BUILDKITE_BUILD_CHECKOUT_PATH}/tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc"
+              mkdir -p "$$artifact_dir"
+              cp -v tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc/*.json "$$artifact_dir/"
+            fi
+
+      - label: "Qwen3-Omni Documentation Examples"
+        agent_pool: mi300_2
+        depends_on: amd-build
+        mirror_hardwares: [amdproduction]
+        grade: NonBlocking
+        timeout_in_minutes: 120
+        commands:
+          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
+          - pytest -s -v tests/examples/online_serving/test_qwen3_omni.py -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"
+
+      - label: "Qwen3-Omni AITER-on Smoke"
+        agent_pool: mi300_2
+        depends_on: amd-build
+        mirror_hardwares: [amdproduction]
+        grade: NonBlocking
+        timeout_in_minutes: 90
+        commands:
+          - export VLLM_ROCM_USE_AITER=1
+          - pytest -s -v tests/e2e/online_serving/test_qwen3_omni_expansion.py::test_text_to_text_audio_001 -m "full_model and rocm and MI325 and cards_2" --run-level "full_model"

.buildkite/common/scripts/skip_ci.py

@@ -44,6 +44,7 @@ L3_YAML_FILES: dict[str, str] = {
 L45_YAML_FILES: dict[str, str] = {
     ".buildkite/cuda/test-nightly.yml": "cuda",
     ".buildkite/cuda/test-weekly.yml": "cuda",
+    ".buildkite/amd/test-amd-nightly.yml": "amd",
     ".buildkite/npu/test-npu-nightly.yml": "npu",
 }
 

docs/contributing/ci/ci_settings.md

@@ -35,6 +35,7 @@ Canonical layout (prefer these paths for new changes):
 ├── amd/
 │   ├── test-amd-ready.yml           # L2 job definitions (template input)
 │   ├── test-amd-merge.yml           # L3 job definitions
+│   ├── test-amd-nightly.yml         # Nightly full-model jobs (experimental)
 │   ├── test-template-amd-omni.j2    # Renders final pipeline.yaml
 │   └── scripts/
 │       ├── bootstrap-amd-omni.sh    # Entry: skip-ci → Jinja → upload
@@ -64,7 +65,7 @@ Canonical layout (prefer these paths for new changes):
 | -------- | ---------------- | -------------- | ---------------- | -------------------- |
 | **CUDA** | `cuda/pipeline.yml` | `test-ready.yml`, `test-merge.yml`, `test-nightly.yml`, `test-weekly.yml` | `upload_pipeline.py --upload` (expands uploader-only keys) | omit `mirror_hardwares` (from `-m`) / preset string + `MIRROR_HW` |
 | **NPU** | `npu/pipeline-npu.yml` | `test-npu-ready.yml`, `test-npu-nightly.yml` | `upload_pipeline.py --upload` | `mirror_hardwares: a2b3_npu_1` / `a2b3_npu_4` / `a3_npu_2` |
-| **AMD** | `amd/scripts/bootstrap-amd-omni.sh` | `test-amd-ready.yml`, `test-amd-merge.yml` | Jinja (`test-template-amd-omni.j2`) → `pipeline upload` | `agent_pool` + `mirror_hardwares: [amdproduction]` (array, template filter) |
+| **AMD** | `amd/scripts/bootstrap-amd-omni.sh` | `test-amd-ready.yml`, `test-amd-merge.yml`, `test-amd-nightly.yml` | Jinja (`test-template-amd-omni.j2`) → `pipeline upload` | `agent_pool` + `mirror_hardwares: [amdproduction]` (array, template filter) |
 | **Intel** | `intel/scripts/bootstrap-intel-omni.sh` | `intel/pipeline-intel.yml` (steps inline) | Direct `pipeline upload` | Inline `agents.queue` on each step |
 
 ## Platform configuration style
@@ -171,9 +172,9 @@ Canonical layout (prefer these paths for new changes):
 
     **Bootstrap:** [`amd/scripts/bootstrap-amd-omni.sh`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/amd/scripts/bootstrap-amd-omni.sh)—skip-ci, diff filtering, Jinja render, then `buildkite-agent pipeline upload`.
 
-    **Test YAML (data):** `amd/test-amd-ready.yml` (L2 / `ready`), `test-amd-merge.yml` (L3 / `merge-test` and `main`). On a PR carrying both labels, AMD combines both suites behind one image build. PR builds without either tier label retain the legacy L2 fallback for compatibility with the `amd-test` trigger. `DEBUG_TEST_YAML` remains an explicit override. AMD has no L4 file yet, so `nightly-test` does not select an additional suite.
+    **Test YAML (data):** `amd/test-amd-ready.yml` (L2 / `ready`), `test-amd-merge.yml` (L3 / `merge-test` and ordinary `main`), and experimental `test-amd-nightly.yml` (`full_model` / `nightly-test` or `main` with `NIGHTLY=1`). Multiple PR tier labels combine their suites behind one image build. PR builds that reach the bootstrap without a tier label retain the legacy ready-suite fallback. `DEBUG_TEST_YAML` accepts `ready`, `merge`, and `nightly` as an explicit override. During nightly burn-in every AMD nightly leaf is non-blocking.
 
-    **Trigger boundary:** AMD label handling has two layers. First, the external `vllm-omni-amd-ci` Buildkite pipeline condition decides whether a GitHub label event creates a build. Only after that build starts does this repository's bootstrap inspect all current PR labels and select L2, L3, or both. Repository-side selection therefore cannot make a `merge-test` event start AMD CI by itself. The external condition must admit both `ready` and `merge-test`, while preserving the legacy `amd-test` trigger and non-PR `main` / scheduled builds. For PR builds without a `DEBUG_TEST_YAML` override, an unreadable label set fails the bootstrap instead of silently selecting the wrong tier. Debug overrides skip label lookup and are validated directly; invalid values, including whitespace-only values, fail the bootstrap. Keep `nightly-test` out of the AMD condition until an AMD L4 suite exists; otherwise it would start a build without providing nightly coverage.
+    **Trigger boundary:** AMD label handling has two layers. First, the external `vllm-omni-amd-ci` Buildkite pipeline condition decides whether a GitHub label event creates a build. Only after that build starts does this repository's bootstrap inspect all current PR labels and select the ready, merge, nightly, or combined suites. Repository-side selection therefore cannot start AMD CI by itself. AMD-only nightly validation uses both `amd-test` and `nightly-test`: the external condition should accept an event for either label only when the complete PR label set contains both. `amd-test` admits the AMD pipeline, while `nightly-test` makes the bootstrap select `NIGHTLY_TESTS:test-amd-nightly.yml`. Existing `ready` / `merge-test` behavior and non-PR `main` / scheduled builds remain separate. For PR builds without a `DEBUG_TEST_YAML` override, an unreadable label set fails the bootstrap instead of silently selecting the wrong tier. Debug overrides skip label lookup and are validated directly; invalid values, including whitespace-only values, fail the bootstrap. Until the paired-label condition is configured, use an authorized manual Buildkite build with `DEBUG_TEST_YAML=nightly` and verify that the bootstrap reports only the nightly suite.
 
     **Rendering:** [`test-template-amd-omni.j2`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/amd/test-template-amd-omni.j2) wraps data steps with `amd-build` image build and `amd_<agent_pool>` queues. Do **not** hand-edit generated `pipeline.yaml`.
 
@@ -189,7 +190,7 @@ Canonical layout (prefer these paths for new changes):
 
     **Adding a job**
 
-    1. Edit `test-amd-ready.yml` or `test-amd-merge.yml`.
+    1. Edit `test-amd-ready.yml`, `test-amd-merge.yml`, or `test-amd-nightly.yml`.
     2. Copy a neighboring block: `label`, `agent_pool`, `mirror_hardwares`, `commands`, optional `grade`.
     3. Regenerate via bootstrap / Jinja; update `skip_ci.py` if you add a new YAML path.
 
@@ -245,7 +246,7 @@ Label triggers (`ready`, `merge-test`) are unchanged—diff-aware logic only red
 | Non-qualifying skip-mark and no CI YAML | normal CI | all on |
 | Diff unavailable | normal CI | all on |
 
-**`skip_all` exceptions (CUDA/NPU bootstrap only):** PR labels (`nightly-test`, `merge-test`, `weekly-test`, `ready`, …) do **not** revive jobs under `skip_all`. On `main`, scheduled `NIGHTLY=1` still builds the image and uploads L4; `WEEKLY=1` or `NON_CRITICAL=1` still builds the image and uploads L5 (CUDA). `WEEKLY=1` on `main` also uploads L2/L3 with `--e2e`.
+**`skip_all` exceptions:** For CUDA/NPU, PR labels (`nightly-test`, `merge-test`, `weekly-test`, `ready`, …) do **not** revive jobs under `skip_all`; on `main`, scheduled `NIGHTLY=1` still builds the image and uploads L4, while `WEEKLY=1` or `NON_CRITICAL=1` still builds the image and uploads L5 (CUDA). `WEEKLY=1` on `main` also uploads L2/L3 with `--e2e`. AMD applies `skip_ci.py gate` only to selected ready/merge specs, so an explicitly selected AMD nightly spec (`nightly-test`, `NIGHTLY=1`, or a nightly debug override) remains runnable even for a docs-only diff.
 
 **Yaml-gated nightly/weekly:** L4/L5 upload steps keep their normal label / `NIGHTLY` / `WEEKLY` / `NON_CRITICAL` conditions (for example PR `nightly-test` still uploads nightly). Only L2/L3 upload steps are matrix-gated.
 
@@ -262,6 +263,7 @@ Register new files in `L2_YAML_FILES`, `L3_YAML_FILES`, or `L45_YAML_FILES` in `
 | L3 | `.buildkite/cuda/test-merge.yml` | cuda |
 | L3 | `.buildkite/amd/test-amd-merge.yml` | amd |
 | L4/L5 | `.buildkite/cuda/test-nightly.yml`, `test-weekly.yml` | cuda |
+| L4/L5 | `.buildkite/amd/test-amd-nightly.yml` | amd |
 | L4/L5 | `.buildkite/npu/test-npu-nightly.yml` | npu |
 
 ##### Yaml-gated category branches
@@ -294,7 +296,7 @@ Docs/skip-mark mixed with any row below follows the same matrix.
 | CUDA ready + AMD merge | G4 | `cuda/l2` + `amd/l3` |
 | CUDA ready + AMD ready | G2 | `cuda/l2` + `amd/l2` |
 | CUDA merge + AMD merge | G3 | `cuda/l3` + `amd/l3` |
-| Only nightly / weekly / npu-nightly YAML | G1 | (none) |
+| Only nightly / weekly / amd-nightly / npu-nightly YAML | G1 | (none) |
 | CUDA ready + nightly | G5 | `cuda/l2` |
 | CUDA merge + nightly | G6 | `cuda/l3` |
 | CUDA ready + merge + nightly | G7 | `cuda/l2` + `cuda/l3` |

docs/contributing/ci/test_system_overview.md

@@ -182,6 +182,8 @@ CUDA **L4** (`full_model`) jobs are defined once in [`.buildkite/cuda/test-night
 - **Nightly:** scheduled `main` builds with `NIGHTLY=1` (and PR labels such as `nightly-test` / `omni-test`). Default fleet is typically H100.
 - **Pre-release:** the same L4 suite runs again on extra GPU SKUs before a release (for example B200 via `MIRROR_HW=b200`), so `full_model` coverage is not limited to the nightly machine type.
 
+AMD has an experimental, non-blocking `full_model` nightly vertical slice in [`.buildkite/amd/test-amd-nightly.yml`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/amd/test-amd-nightly.yml). It selects ROCm Qwen3-Omni function-expansion, accuracy, documentation-example, and AITER-on smoke coverage on the MI300 pool. AMD-only PR validation uses `amd-test` to admit the external AMD pipeline and `nightly-test` to select this suite; scheduled `main` builds select it with `NIGHTLY=1`. Keep it non-blocking while the lane accumulates stability and completion-time evidence.
+
 How count-form `mirror_hardwares` and `MIRROR_HW` pick a SKU: [CI Settings](./ci_settings.md).
 
 ### L2 / L3 diff-aware CI (CUDA)

tests/buildkite/test_amd_bootstrap.py

@@ -136,7 +136,7 @@ def test_label_lookup_selects_tiers(tmp_path, labels, expected_levels):
     ] == expected_levels
 
 
-@pytest.mark.parametrize("debug_test_yaml", ["ready,ready", "nightly", ", ,", " \t"])
+@pytest.mark.parametrize("debug_test_yaml", ["ready,ready", "nightly,nightly", ", ,", " \t"])
 def test_invalid_debug_override_fails_without_label_lookup(tmp_path, debug_test_yaml):
     result = _run_bootstrap(tmp_path, debug_test_yaml=debug_test_yaml, curl_status=22)
 

tests/buildkite/test_amd_pipeline.py

@@ -10,10 +10,11 @@ import yaml
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 
 AMD_MERGE_PIPELINE = Path(".buildkite/amd/test-amd-merge.yml")
+AMD_NIGHTLY_PIPELINE = Path(".buildkite/amd/test-amd-nightly.yml")
 
 
-def _find_step(label: str) -> dict:
-    pipeline = yaml.safe_load(AMD_MERGE_PIPELINE.read_text(encoding="utf-8"))
+def _find_step(label: str, pipeline_path: Path = AMD_MERGE_PIPELINE) -> dict:
+    pipeline = yaml.safe_load(pipeline_path.read_text(encoding="utf-8"))
 
     def walk(steps: list[dict]) -> dict | None:
         for step in steps:
@@ -40,3 +41,15 @@ def test_qwen3_tts_base_preserves_advanced_model_arguments() -> None:
     run_level_index = argv.index("--run-level")
     assert argv[marker_index + 1] == "advanced_model and cuda"
     assert argv[run_level_index + 1] == "advanced_model"
+
+
+def test_qwen3_accuracy_defers_artifact_path_expansion() -> None:
+    step = _find_step("Qwen3-Omni Accuracy", AMD_NIGHTLY_PIPELINE)
+    staging_command = next(command for command in step["commands"] if "artifact_dir=" in command)
+
+    # Dynamic pipelines are interpolated once during upload. Double dollars
+    # preserve these variables for the GPU job's runtime shell.
+    assert '"$$PWD"' in staging_command
+    assert '"$${BUILDKITE_BUILD_CHECKOUT_PATH:?}"' in staging_command
+    assert '"$$artifact_dir"' in staging_command
+    assert step["artifact_paths"] == ["tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc/*.json"]

tests/buildkite/test_amd_suite_selection.py

@@ -24,10 +24,12 @@ SPEC.loader.exec_module(SELECTOR)
         ("feature", ("ready",), ("ready",)),
         ("feature", ("merge-test",), ("merge",)),
         ("feature", ("merge-test", "ready"), ("ready", "merge")),
+        ("feature", ("nightly-test",), ("nightly",)),
+        ("feature", ("ready", "merge-test", "nightly-test"), ("ready", "merge", "nightly")),
         ("feature", ("amd-test",), ("ready",)),
         ("feature", ("amd-test", "merge-test"), ("merge",)),
         ("feature", ("amd-test", "ready", "merge-test"), ("ready", "merge")),
-        ("feature", ("nightly-test",), ("ready",)),
+        ("feature", ("amd-test", "nightly-test"), ("nightly",)),
         ("feature", ("not-ready", "merge-test-extra"), ("ready",)),
     ],
 )
@@ -39,8 +41,17 @@ def test_debug_override_takes_precedence_and_normalizes_input():
     assert SELECTOR.select_amd_test_suites(
         branch="main",
         labels=("ready",),
-        debug_test_yaml=" MERGE, ready,",
-    ) == ("merge", "ready")
+        debug_test_yaml=" NIGHTLY, merge, ready,",
+        nightly=False,
+    ) == ("nightly", "merge", "ready")
+
+
+def test_scheduled_main_selects_only_nightly():
+    assert SELECTOR.select_amd_test_suites(
+        branch="main",
+        labels=(),
+        nightly=True,
+    ) == ("nightly",)
 
 
 def test_empty_debug_override_uses_normal_selection():
@@ -51,7 +62,7 @@ def test_empty_debug_override_uses_normal_selection():
     ) == ("merge",)
 
 
-@pytest.mark.parametrize("value", ["ready,ready", "nightly", ", ,", " \t"])
+@pytest.mark.parametrize("value", ["ready,ready", "nightly,nightly", "weekly", ", ,", " \t"])
 def test_invalid_debug_override(value):
     with pytest.raises(ValueError):
         SELECTOR.select_amd_test_suites(

tests/buildkite/test_skip_ci.py

@@ -144,6 +144,14 @@ def test_npu_nightly_only_skips_all_l23() -> None:
     assert not decision.is_run("npu", "l3")
 
 
+def test_amd_nightly_only_skips_all_l23() -> None:
+    decision = _decision([".buildkite/amd/test-amd-nightly.yml"])
+    assert _is_yaml_gated(decision)
+    assert _all_l23_skipped(decision)
+    assert not decision.is_run("amd", "l2")
+    assert not decision.is_run("amd", "l3")
+
+
 def test_nightly_and_weekly_skips_all_l23() -> None:
     decision = _decision(
         [