[Hardware][Ascend] Enable VoxCPM2 eager optimizations (#7207)

Signed-off-by: Big2Wheel <1404207590@qq.com>

tests/e2e/offline_inference/test_voxcpm2_tts.py

@@ -13,7 +13,7 @@ from tests.helpers.mark import hardware_test
 from tests.helpers.runtime import OmniRunner
 from tests.helpers.stage_config import get_deploy_config_path
 
-VOXCPM2_MODEL = "openbmb/VoxCPM2"
+VOXCPM2_MODEL = os.environ.get("VOXCPM2_MODEL", "openbmb/VoxCPM2")
 DEPLOY_CONFIG = get_deploy_config_path("voxcpm2.yaml")
 SAMPLE_RATE = 48000
 
@@ -44,7 +44,7 @@ def _extract_audio(multimodal_output: dict) -> torch.Tensor:
 
 @pytest.mark.slow
 @pytest.mark.tts
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
+@hardware_test(res={"cuda": "L4", "npu": "A2"}, num_cards=1)
 def test_voxcpm2_zero_shot_001(omni_runner: OmniRunner) -> None:
     """Test zero-shot TTS produces valid audio output."""
     outputs = omni_runner.omni.generate([{"prompt": "Hello, this is a test."}])
@@ -57,7 +57,7 @@ def test_voxcpm2_zero_shot_001(omni_runner: OmniRunner) -> None:
 
 @pytest.mark.slow
 @pytest.mark.tts
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
+@hardware_test(res={"cuda": "L4", "npu": "A2"}, num_cards=1)
 def test_voxcpm2_voice_clone_002(omni_runner: OmniRunner) -> None:
     """Test voice cloning with a reference audio file.
 
@@ -98,7 +98,7 @@ def test_voxcpm2_voice_clone_002(omni_runner: OmniRunner) -> None:
 
 @pytest.mark.slow
 @pytest.mark.tts
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
+@hardware_test(res={"cuda": "L4", "npu": "A2"}, num_cards=1)
 def test_voxcpm2_prefill_decode_mixed_batch_003(omni_runner: OmniRunner) -> None:
     """Regression: prefill+decode mixed batch must not crash (PR #2903)."""
     long_prompt = (

tests/e2e/online_serving/test_voxcpm2_tts.py

@@ -18,7 +18,7 @@ from tests.helpers.mark import hardware_test
 from tests.helpers.runtime import OmniServerParams
 from tests.helpers.stage_config import get_deploy_config_path
 
-MODEL = "openbmb/VoxCPM2"
+MODEL = os.environ.get("VOXCPM2_MODEL", "openbmb/VoxCPM2")
 DEFAULT_AUDIO_SPEECH_TIMEOUT_S = 300.0
 MAX_CONCURRENT = 4
 
@@ -48,7 +48,7 @@ tts_server_params = [
 
 @pytest.mark.slow
 @pytest.mark.tts
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
+@hardware_test(res={"cuda": "L4", "npu": "A2"}, num_cards=1)
 @pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
 def test_text_to_audio_001(omni_server, online_client) -> None:
     """
@@ -73,7 +73,7 @@ def test_text_to_audio_001(omni_server, online_client) -> None:
 
 @pytest.mark.slow
 @pytest.mark.tts
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
+@hardware_test(res={"cuda": "L4", "npu": "A2"}, num_cards=1)
 @pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
 def test_text_to_audio_002(omni_server, online_client) -> None:
     """

tests/e2e/online_serving/test_voxcpm2_tts_expansion.py

@@ -20,7 +20,7 @@ pytestmark = [pytest.mark.slow, pytest.mark.tts]
 
 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
 
-MODEL = "openbmb/VoxCPM2"
+MODEL = os.environ.get("VOXCPM2_MODEL", "openbmb/VoxCPM2")
 DEFAULT_AUDIO_SPEECH_TIMEOUT_S = 300.0
 _MIN_AUDIO_BYTES = 40_000
 MAX_CONCURRENT = 4
@@ -47,7 +47,7 @@ tts_server_params = [
 ]
 
 
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
+@hardware_test(res={"cuda": "L4", "npu": "A2"}, num_cards=1)
 @pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
 def test_voice_clone_streaming_001(omni_server, online_client) -> None:
     """
@@ -72,7 +72,7 @@ def test_voice_clone_streaming_001(omni_server, online_client) -> None:
     online_client.send_audio_speech_request(request_config, request_num=MAX_CONCURRENT)
 
 
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
+@hardware_test(res={"cuda": "L4", "npu": "A2"}, num_cards=1)
 @pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
 def test_response_format_001(omni_server, online_client) -> None:
     """

tests/model_executor/models/voxcpm2/test_talker_state_eviction.py

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 """Regression tests for VoxCPM2 talker per-request state lifecycle."""
 
 from __future__ import annotations
@@ -72,6 +72,99 @@ def _seed_cached_decode(talker, req_id: str):
 
 
 class TestStateEvictionContract:
+    def test_eager_optimizations_do_not_require_torch_inductor(self, monkeypatch) -> None:
+        from vllm_omni.model_executor.models.voxcpm2 import voxcpm2_talker as tk
+
+        class FakeEstimator:
+            pass
+
+        class FakeFeatDecoder:
+            def __init__(self, estimator) -> None:
+                self.estimator = estimator
+                self.mean_mode = False
+
+        class FakeTTS:
+            def __init__(self, estimator) -> None:
+                self.feat_decoder = FakeFeatDecoder(estimator)
+
+        talker = _make_bare_talker()
+        estimator = FakeEstimator()
+        talker._tts = FakeTTS(estimator)
+        _, _, RuntimeConfig = _voxcpm2_talker_mod()
+        talker._runtime_config = RuntimeConfig()
+        talker._enable_torch_compile = False
+
+        applied: list[str] = []
+
+        def install_qkv(*_args, **_kwargs) -> int:
+            applied.append("qkv")
+            return 12
+
+        def install_mlp(*_args, **_kwargs) -> int:
+            applied.append("mlp")
+            return 12
+
+        def install_zero_dt(*_args, **_kwargs) -> bool:
+            applied.append("zero_dt")
+            return True
+
+        monkeypatch.setattr(
+            tk,
+            "_install_locdit_fused_qkv",
+            install_qkv,
+        )
+        monkeypatch.setattr(
+            tk,
+            "_install_locdit_fused_mlp",
+            install_mlp,
+        )
+        monkeypatch.setattr(
+            tk,
+            "_install_locdit_zero_dt_cache",
+            install_zero_dt,
+        )
+
+        talker._setup_execution_optimizations()
+
+        assert applied == ["qkv", "mlp", "zero_dt"]
+        assert talker._eager_optimizations_applied is True
+        assert not hasattr(estimator, "_compiled")
+
+    def test_profiler_drops_invalid_accelerator_graph_events(self, monkeypatch) -> None:
+        from vllm_omni.model_executor.models.voxcpm2 import voxcpm2_talker as tk
+
+        timer = tk._PerfTimer(enabled=False)
+        timer._enabled = True
+
+        class InvalidEvent:
+            def elapsed_time(self, _end) -> float:
+                raise RuntimeError("event recorder null")
+
+        timer._pairs.append(("captured", InvalidEvent(), object()))
+        monkeypatch.setattr(torch.accelerator, "synchronize", lambda: None)
+
+        assert timer.breakdown() == ""
+        assert timer._pairs == []
+
+    def test_profiler_disables_device_without_timing_events(self, monkeypatch) -> None:
+        from vllm_omni.model_executor.models.voxcpm2 import voxcpm2_talker as tk
+
+        class DeviceWithoutEvents:
+            pass
+
+        monkeypatch.setattr(
+            torch,
+            "get_device_module",
+            lambda _device: DeviceWithoutEvents(),
+        )
+
+        timer = tk._PerfTimer(enabled=True)
+        timer.start("cpu")
+
+        assert timer._enabled is False
+        assert timer._device_module is None
+        assert timer._starts == {}
+
     def test_runtime_config_normalizes_mutually_exclusive_paths(self) -> None:
         _, _, RuntimeConfig = _voxcpm2_talker_mod()
 
@@ -295,6 +388,7 @@ class TestChunkedPrefillContract:
         talker._get_multichar_zh_split = lambda: {}
         talker._perf = _NoopPerf()
         talker._enable_torch_compile = False
+        talker._setup_execution_optimizations = lambda: None
         talker._setup_cfm_buffers = lambda: None
         talker._run_cfm_for_state = lambda *_args: torch.ones(1, 1, 4)