[Misc] Remove Dynin-Omni and dots.tts support (#7655)

Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>

tests/model_executor/models/dots_tts/__init__.py

@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

tests/model_executor/models/dots_tts/test_talker.py

@@ -1,137 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""Regression tests for the dots.tts talker's stop-signal pairing and
-per-request state lifecycle.
-
-Pure-CPU tests on a bare talker (``__new__`` + the handful of attributes
-the methods under test read) — no weights, no GPU, no engine.  Mirrors
-tests/model_executor/models/voxcpm2/test_talker_state_eviction.py.
-"""
-
-from __future__ import annotations
-
-import functools
-from types import SimpleNamespace
-
-import pytest
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
-
-
-torch = pytest.importorskip("torch")
-
-_VOCAB_SIZE = 151672
-
-
-@functools.lru_cache(maxsize=1)
-def _dots_tts_talker_mod():
-    """Defer talker import (pulls vLLM model_executor) until first use."""
-    from vllm_omni.model_executor.models.dots_tts.dots_tts_talker import (
-        DotsTTSForConditionalGeneration,
-        _RequestState,
-    )
-
-    return DotsTTSForConditionalGeneration, _RequestState
-
-
-def _make_bare_talker():
-    DotsTTSForConditionalGeneration, _ = _dots_tts_talker_mod()
-    talker = DotsTTSForConditionalGeneration.__new__(DotsTTSForConditionalGeneration)
-    talker.config = SimpleNamespace(vocab_size=_VOCAB_SIZE)
-    talker._active_states = {}
-    talker._pending_requests = []
-    talker._results_queue = []
-    talker._audio_queue = []
-    talker._deferred_cleanup_ids = set()
-    talker._beta_trace = False
-    return talker
-
-
-def _add_state(talker, req_id: str, *, is_stopping: bool = False):
-    _, _RequestState = _dots_tts_talker_mod()
-    state = _RequestState(request_id=req_id)
-    state.prefill_completed = True
-    state.is_stopping = is_stopping
-    talker._active_states[req_id] = state
-    return state
-
-
-def _hidden(bsz: int) -> torch.Tensor:
-    return torch.zeros(bsz, 1536, dtype=torch.float32)
-
-
-class TestComputeLogitsPairing:
-    """compute_logits pairs _results_queue entries with batch rows
-    positionally, so every request must push exactly one entry per step —
-    including prefills, which push a (req_id, None) placeholder."""
-
-    def test_mixed_batch_prefill_placeholder_keeps_rows_aligned(self) -> None:
-        talker = _make_bare_talker()
-        _add_state(talker, "prefill-req")
-        decode_state = _add_state(talker, "decode-req", is_stopping=True)
-        decode_state.precomputed_stop_logits = torch.tensor([[0.1, 0.9]])
-
-        # Row 0 is the prefill (None placeholder), row 1 the stopping decode.
-        talker._results_queue = [
-            ("prefill-req", None),
-            ("decode-req", torch.tensor([[0.1, 0.9]])),
-        ]
-        logits = talker.compute_logits(_hidden(2))
-
-        assert logits.shape == (2, _VOCAB_SIZE)
-        # Prefill row: forced continue.
-        assert logits[0, 0].item() == 1.0
-        assert logits[0, 1].item() == float("-inf")
-        # Stopping decode row: stop slot wins.
-        assert logits[1, 1].item() == 1.0
-        assert logits[1, 0].item() == 0.0
-        # Everything else stays masked.
-        assert logits[0, 2].item() == float("-inf")
-        assert logits[1, 2].item() == float("-inf")
-        # Queue drained.
-        assert talker._results_queue == []
-
-    def test_below_threshold_stop_logits_force_continue(self) -> None:
-        """Raw (continue, stop) softmax must not reach the sampler: a
-        prob_stop in (0.5, 0.8] would flip greedy argmax even though
-        is_stopping stayed False (the 0.8-threshold contract)."""
-        talker = _make_bare_talker()
-        _add_state(talker, "req", is_stopping=False)
-        talker._results_queue = [("req", torch.tensor([[0.3, 0.7]]))]
-
-        logits = talker.compute_logits(_hidden(1))
-
-        assert logits[0, 0].item() == 1.0
-        assert logits[0, 1].item() == float("-inf")
-
-    def test_empty_queue_defaults_to_all_continue(self) -> None:
-        talker = _make_bare_talker()
-        logits = talker.compute_logits(_hidden(3))
-
-        assert torch.all(logits[:, 0] == 1.0)
-        assert torch.all(logits[:, 1] == float("-inf"))
-
-
-class TestStateEviction:
-    """on_requests_finished fires BEFORE forward(), so eviction must be
-    deferred to _flush_deferred_cleanup at the end of the step — the
-    finishing request's audio still drains through the current forward."""
-
-    def test_finished_request_survives_until_flush(self) -> None:
-        talker = _make_bare_talker()
-        _add_state(talker, "req-a")
-        _add_state(talker, "req-b")
-
-        talker.on_requests_finished(["req-a"])
-        assert "req-a" in talker._active_states  # not evicted yet
-
-        talker._flush_deferred_cleanup()
-        assert "req-a" not in talker._active_states
-        assert "req-b" in talker._active_states
-        assert talker._deferred_cleanup_ids == set()
-
-    def test_unknown_request_id_is_ignored(self) -> None:
-        talker = _make_bare_talker()
-        talker.on_requests_finished(["never-seen"])
-        talker._flush_deferred_cleanup()
-        assert talker._active_states == {}

tests/model_executor/models/dynin_omni/test_dynin_omni_token2audio.py

@@ -1,40 +0,0 @@
-from __future__ import annotations
-
-import pytest
-from transformers import PreTrainedModel
-
-from vllm_omni.model_executor.models.dynin_omni.dynin_omni_token2audio import (
-    _ensure_transformers_tied_weights_compat,
-)
-
-pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
-
-
-def test_transformers_tied_weights_compat(monkeypatch):
-    """Compat shim must not permanently mutate ``PreTrainedModel``.
-
-    ``monkeypatch.delattr(..., raising=False)`` is a no-op undo when the attr
-    was absent. ``_ensure_transformers_tied_weights_compat`` then assigns a
-    read-only ``property`` on the class that later PreTrainedModel subclasses
-    (e.g. qwen3 TTS mask-cache) can trip over with
-    ``AttributeError: property ... has no setter``.
-    """
-    monkeypatch.delattr(PreTrainedModel, "all_tied_weights_keys", raising=False)
-
-    _ensure_transformers_tied_weights_compat()
-    installed = PreTrainedModel.__dict__.get("all_tied_weights_keys")
-    assert installed is not None
-
-    # Re-own the installed descriptor through monkeypatch so teardown always
-    # removes/restores it, even when the attr did not exist before this test.
-    delattr(PreTrainedModel, "all_tied_weights_keys")
-    monkeypatch.setattr(PreTrainedModel, "all_tied_weights_keys", installed, raising=False)
-
-    model = PreTrainedModel.__new__(PreTrainedModel)
-    model._tied_weights_keys = ["decoder.weight"]
-    model._dynamic_tied_weights_keys = {"lm_head.weight": "decoder.weight"}
-
-    assert model.all_tied_weights_keys == {
-        "decoder.weight": None,
-        "lm_head.weight": "decoder.weight",
-    }

tests/model_executor/stage_input_processors/test_qwen3_omni_streaming_helpers.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
 """Unit tests for Qwen3-Omni streaming thinker→talker / talker→codec helpers (PR #2581)."""
 
 from __future__ import annotations
@@ -356,7 +356,7 @@ def test_accumulator_concat_default_when_no_replace_keys() -> None:
     class _StubMixin(OmniConnectorModelRunnerMixin):
         def __init__(self):
             self._pending_full_payload_send = {}
-            self._full_payload_replace_keys_cached = frozenset()
+            self._full_payload_replace_keys_cached: frozenset[str] = frozenset()
 
     stub = _StubMixin()
     stub.accumulate_full_payload_output(
@@ -415,51 +415,6 @@ def test_covo_audio_llm2code2wav_full_payload_smoke() -> None:
     assert payload["meta"]["finished"].item() is True
 
 
-def test_dynin_omni_token_only_smoke() -> None:
-    """Smoke: dynin_omni token-only builders return placeholders."""
-    from vllm_omni.model_executor.stage_input_processors.dynin_omni import (
-        token2text_to_token2image_token_only,
-    )
-
-    class _Out:
-        def __init__(self, tids, mm=None):
-            self.token_ids = tids
-            self.multimodal_output = mm
-
-    class _Wrapper:
-        def __init__(self, tids, mm=None):
-            self.outputs = [_Out(tids, mm)]
-            self.request_id = "r0"
-
-    class _Stage:
-        def __init__(self, outs):
-            self.engine_outputs = outs
-
-    src = [_Wrapper([10, 11, 12])]
-    out = token2text_to_token2image_token_only([_Stage(src)], [0])
-    assert len(out) == 1
-    assert len(out[0]["prompt_token_ids"]) == 3
-    assert out[0]["additional_information"] is None
-
-
-def test_dynin_omni_full_payload_smoke() -> None:
-    """Smoke: dynin_omni producer-side payload builder returns nested OmniPayload + carries metadata."""
-    from types import SimpleNamespace
-
-    from vllm_omni.model_executor.stage_input_processors.dynin_omni import (
-        token2text_to_token2image_full_payload,
-    )
-
-    pooling = {"token_ids": [1, 2, 3]}
-    req = SimpleNamespace(output_token_ids=[], additional_information={"speaker": ["alice"]})
-    payload = token2text_to_token2image_full_payload(None, pooling, req)
-    assert payload is not None
-    assert payload["codes"]["audio"] == [1, 2, 3]
-    assert payload["meta"]["finished"].item() is True
-    # additional_information is normalized + carried forward (speaker stays list-wrapped).
-    assert payload.get("speaker") == ["alice"]
-
-
 def test_qwen2_5_omni_talker2code2wav_token_only_smoke() -> None:
     """Smoke: qwen2_5_omni talker→code2wav token_only marker + boundary strip."""
     from vllm_omni.model_executor.stage_input_processors.qwen2_5_omni import (