[Rebase] Rebase to vllm 0.27.0 (#5976)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

tests/diffusion/distributed/test_expert_parallel_layout.py

@@ -64,6 +64,7 @@ def test_moe_ep_maps_diffusion_sp_cfg_dp_to_vllm_groups(monkeypatch):
         local_rank,
         backend,
         group_name,
+        use_all2all=False,
     ):
         del backend
         group = _FakeGroup(
@@ -73,6 +74,7 @@ def test_moe_ep_maps_diffusion_sp_cfg_dp_to_vllm_groups(monkeypatch):
             device_communicator=object(),
             reduce_scatter=lambda tensor, **kwargs: tensor,
         )
+        group.use_all2all = use_all2all
         created_groups.append(group)
         return group
 
@@ -121,6 +123,9 @@ def test_moe_ep_maps_diffusion_sp_cfg_dp_to_vllm_groups(monkeypatch):
     assert parallel_state.vllm_parallel_state._PCP.device_communicator is not None
     assert parallel_state.vllm_parallel_state._DP.device_communicator is not None
     assert parallel_state.vllm_parallel_state._EP.device_communicator is not None
+    # vLLM 0.27's MoE oracle asserts the EP communicator has an all2all
+    # manager, which vLLM only builds for groups created with use_all2all.
+    assert parallel_state.vllm_parallel_state._EP.use_all2all is True
     assert hasattr(parallel_state.vllm_parallel_state._PCP, "reduce_scatter")
     assert hasattr(parallel_state.vllm_parallel_state._DP, "reduce_scatter")
     assert hasattr(parallel_state.vllm_parallel_state._EP, "reduce_scatter")
@@ -313,3 +318,35 @@ def test_non_moe_ep_fails_before_vllm_ep_remap(monkeypatch):
     assert parallel_state.vllm_parallel_state._PCP is None
     assert parallel_state.vllm_parallel_state._EP is None
     assert parallel_state._EXPERT_PARALLEL_GROUP_RANKS is None
+
+
+@pytest.mark.cpu
+@pytest.mark.core_model
+def test_init_vllm_group_forwards_use_all2all_only_when_supported(monkeypatch):
+    """use_all2all reaches vLLM only on versions whose API accepts it.
+
+    vLLM 0.27 builds the EP all2all manager only for groups created with
+    use_all2all=True (its MoE oracle then asserts the manager exists —
+    build 2953, HunyuanImage3-DIT accuracy). Older vLLM has no such kwarg,
+    so forwarding it unconditionally would TypeError at init.
+    """
+    received = {}
+
+    def modern(group_ranks, local_rank, backend, group_name=None, use_device_communicator=True, use_all2all=False):
+        received["modern"] = use_all2all
+        return object()
+
+    monkeypatch.setattr(parallel_state.vllm_parallel_state, "init_model_parallel_group", modern)
+    parallel_state.init_vllm_model_parallel_group([[0]], 0, "gloo", "ep", use_all2all=True)
+    assert received["modern"] is True
+
+    parallel_state.init_vllm_model_parallel_group([[0]], 0, "gloo", "tp")
+    assert received["modern"] is False
+
+    def legacy(group_ranks, local_rank, backend, group_name=None, use_device_communicator=True):
+        received["legacy"] = True
+        return object()
+
+    monkeypatch.setattr(parallel_state.vllm_parallel_state, "init_model_parallel_group", legacy)
+    parallel_state.init_vllm_model_parallel_group([[0]], 0, "gloo", "ep", use_all2all=True)
+    assert received["legacy"] is True

tests/diffusion/layers/test_fused_moe.py

@@ -110,7 +110,7 @@ class TestFusedMoEFactory:
         monkeypatch.setitem(
             sys.modules,
             "vllm.model_executor.layers.fused_moe",
-            SimpleNamespace(FusedMoE=mock_vllm_fused_moe),
+            SimpleNamespace(FusedMoEFactory=mock_vllm_fused_moe),
         )
 
         result = fused_moe.FusedMoE(prefix="test", a=1, reduce_results=True)
@@ -139,7 +139,7 @@ class TestFusedMoEFactory:
         monkeypatch.setitem(
             sys.modules,
             "vllm.model_executor.layers.fused_moe",
-            SimpleNamespace(FusedMoE=mocker.MagicMock(return_value=mock_runner)),
+            SimpleNamespace(FusedMoEFactory=mocker.MagicMock(return_value=mock_runner)),
         )
         mocker.patch.object(fused_moe, "current_omni_platform", mocker.MagicMock())
         mock_set_num_tokens = mocker.patch.object(fused_moe, "_set_forward_context_num_tokens")
@@ -169,7 +169,7 @@ class TestFusedMoEFactory:
         monkeypatch.setitem(
             sys.modules,
             "vllm.model_executor.layers.fused_moe",
-            SimpleNamespace(FusedMoE=mocker.MagicMock(return_value=mock_runner)),
+            SimpleNamespace(FusedMoEFactory=mocker.MagicMock(return_value=mock_runner)),
         )
         mocker.patch.object(fused_moe, "current_omni_platform", mocker.MagicMock())
         mock_set_num_tokens = mocker.patch.object(fused_moe, "_set_forward_context_num_tokens")

tests/diffusion/models/lingbot_video/test_request_utils.py

@@ -348,3 +348,53 @@ def test_normalize_lingbot_request_model_size_overrides_sampling_dimensions():
         num_frames=81,
     )
     assert (config.height, config.width) == (480, 480)
+
+
+def test_normalize_lingbot_request_reads_size_from_extra_args():
+    """Regression: /v1/videos delivers `extra_params` via sampling.extra_args.
+
+    The nightly TI2V case sends `extra_params={"size": "320x192"}` with no
+    height/width form fields; the size used to be dropped and the video came
+    out at the 480x480 default (build 2952, LingBot Video MoE Function Test).
+    """
+    config = _normalize(
+        {
+            "prompt": "motion",
+            "modalities": ["video"],
+            "multi_modal_data": {"image": Image.new("RGB", (320, 192))},
+        },
+        num_frames=9,
+        extra_args={"size": "320x192"},
+    )
+    assert config.mode is LingBotGenerationMode.TI2V
+    assert (config.height, config.width) == (192, 320)
+
+
+def test_normalize_lingbot_request_extra_args_size_overrides_sampling_dimensions():
+    config = _normalize(
+        {"prompt": "motion", "modalities": ["video"]},
+        width=480,
+        height=480,
+        num_frames=81,
+        extra_args={"size": "320x192"},
+    )
+    assert (config.height, config.width) == (192, 320)
+
+
+def test_normalize_lingbot_request_reads_width_height_from_extra_args():
+    # Parity with the pre-#5311 pipeline, which honored extra_args height/width.
+    config = _normalize(
+        {"prompt": "motion", "modalities": ["video"]},
+        num_frames=81,
+        extra_args={"width": 320, "height": 192},
+    )
+    assert (config.height, config.width) == (192, 320)
+
+
+def test_resolve_lingbot_output_dimensions_reads_extra_fields():
+    assert resolve_lingbot_output_dimensions(extra_fields={"size": "320x192"}) == (320, 192)
+    assert resolve_lingbot_output_dimensions(
+        sampling_width=480,
+        sampling_height=480,
+        extra_fields={"resolution": "720p", "ratio": "16:9"},
+    ) == (736, 1280)

tests/diffusion/quantization/test_quantization_quality.py

@@ -515,8 +515,14 @@ def test_quantization_quality(config: QualityTestConfig):
 
     generate_fn = _generate_video if config.task == "t2v" else _generate_image
 
+    # Run both arms eager: LPIPS must measure quantization only. With compile
+    # on, a compiler failure in one arm (e.g. inductor's CantSplit on fp8 FLUX)
+    # silently drops that arm to eager while the other stays compiled, and the
+    # metric then includes compile-state differences (fp8_ltx2 rose from ~0.09
+    # to 0.1291 that way in build 2954). Mirrors
+    # vllm_omni/quantization/tools/compare_diffusion_trajectory_similarity.py.
     # --- BF16 baseline ---
-    bl_kwargs: dict = {"model": config.baseline_ref()}
+    bl_kwargs: dict = {"model": config.baseline_ref(), "enforce_eager": True}
     if config.enable_cpu_offload:
         bl_kwargs["enable_cpu_offload"] = True
     omni_bl = Omni(**bl_kwargs)
@@ -528,7 +534,7 @@ def test_quantization_quality(config: QualityTestConfig):
 
     # --- Quantized ---
     quantization = config.quantization_ref()
-    qt_kwargs: dict = {"model": config.quantized_ref()}
+    qt_kwargs: dict = {"model": config.quantized_ref(), "enforce_eager": True}
     if config.enable_cpu_offload:
         qt_kwargs["enable_cpu_offload"] = True
     if quantization is None:

tests/diffusion/test_compile.py

@@ -74,3 +74,37 @@ def test_regionally_compile_does_not_partially_mutate_on_setup_failure(monkeypat
         regionally_compile(model, dynamic=True)
 
     assert [block.forward.__func__ for block in model.transformer_blocks] == original_forwards
+
+
+def test_compiled_block_preserves_forward_signature_for_inspection(monkeypatch):
+    """cache-dit matches blocks via inspect.signature(block.forward).
+
+    Whatever regionally_compile installs as the block forward must stay
+    signature-transparent: parameter names and the return annotation drive
+    cache-dit's ForwardPattern match (build 2954, Multi-GPU Layered job
+    failed when a bare *args/**kwargs wrapper hid them; torch.compile's own
+    wrapper preserves the signature).
+    """
+    import inspect
+
+    import torch
+
+    class _SignatureBlock(nn.Module):
+        def forward(self, hidden_states, encoder_hidden_states=None) -> "torch.Tensor":
+            return hidden_states
+
+    class _Model(nn.Module):
+        _repeated_blocks = ["_SignatureBlock"]
+
+        def __init__(self) -> None:
+            super().__init__()
+            self.blocks = nn.ModuleList([_SignatureBlock()])
+
+    model = _Model()
+    monkeypatch.setattr(compile_module.torch, "compile", lambda fn, *a, **k: fn)
+    regionally_compile(model)
+
+    sig = inspect.signature(model.blocks[0].forward)
+    assert set(sig.parameters.keys()) == {"hidden_states", "encoder_hidden_states"}
+    assert "torch.Tensor" in str(sig.return_annotation)
+    assert model.blocks[0].forward("x") == "x"

tests/diffusion/test_inductor_divisibility_patch.py

@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Regression tests for the inductor factorable-divisibility patch.
+
+torch 2.13 proves symbolic divisibility with torch's own unevaluated Mod,
+so ``15360*s31 + 15360*s87`` is no longer provably divisible by
+``s31 + s87`` and inductor raises CantSplit on FLUX's fp8 graph (nightly
+builds 2953/2954). The patch adds an exact-polynomial-division proof that
+is sound for every symbol assignment; on torch versions whose original
+check already proves the case (<= 2.11, via sympy.Mod), the patch
+self-extinguishes.
+"""
+
+import pytest
+import sympy
+from torch._inductor.sizevars import SizeVarAllocator
+
+import vllm_omni.patch as patch_module
+
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]
+
+_S1, _S2 = sympy.symbols("s31 s87", positive=True, integer=True)
+
+
+@pytest.mark.parametrize(
+    ("numerator", "denominator", "expected"),
+    [
+        (15360 * _S1 + 15360 * _S2, _S1 + _S2, True),  # the CantSplit expression
+        (7 * _S1 + 7 * _S2, _S1 + _S2, True),
+        (_S1 * _S2, _S2, True),
+        (_S1 * _S2 + _S2, _S2, True),  # s2*(s1 + 1)
+        (3 * _S1, 2 * _S1, False),
+        (_S1 + 1, _S1, False),
+        (15360 * _S1 + 15359 * _S2, _S1 + _S2, False),
+        (sympy.Integer(12), sympy.Integer(4), True),
+        (sympy.Integer(12), sympy.Integer(5), False),
+    ],
+)
+def test_provably_factorable_multiple(numerator, denominator, expected):
+    assert patch_module._provably_factorable_multiple(numerator, denominator) is expected
+
+
+def test_non_polynomial_atoms_never_reach_cancel():
+    from torch.utils._sympy.functions import FloorDiv, ModularIndexing
+
+    assert patch_module._provably_factorable_multiple(FloorDiv(_S1, 2) * 4, _S1) is False
+    assert patch_module._provably_factorable_multiple(ModularIndexing(_S1, 1, 8) * _S2, _S2) is False
+
+
+def test_divisibility_holds_after_patch_regardless_of_torch_version():
+    """The end contract on any torch: the CantSplit expression proves divisible.
+
+    On torch <= 2.11 the original method proves it (patch self-extinguished);
+    on torch >= 2.13 the installed wrapper proves it via exact division.
+    """
+    sv = SizeVarAllocator()
+    method = SizeVarAllocator.statically_known_multiple_of
+    patched = getattr(method, "_vllm_omni_factorable_divisibility", False)
+    assert method(sv, 15360 * _S1 + 15360 * _S2, _S1 + _S2) is True
+    # Negative control must stay non-divisible either way.
+    assert method(sv, 3 * _S1, 2 * _S1) is False
+    if patched:
+        # Wrapper installed: the original alone must have failed the probe.
+        assert patch_module._provably_factorable_multiple(15360 * _S1 + 15360 * _S2, _S1 + _S2) is True
+
+
+def test_patch_installs_when_original_cannot_prove(monkeypatch):
+    """Simulate torch 2.13's unevaluated-Mod prover: the wrapper must install."""
+
+    def weak(self, numerator, denominator):
+        return False
+
+    monkeypatch.setattr(SizeVarAllocator, "statically_known_multiple_of", weak)
+    patch_module._patch_inductor_factorable_divisibility()
+    method = SizeVarAllocator.statically_known_multiple_of
+    assert getattr(method, "_vllm_omni_factorable_divisibility", False) is True
+
+    sv = SizeVarAllocator()
+    assert method(sv, 15360 * _S1 + 15360 * _S2, _S1 + _S2) is True
+    assert method(sv, 3 * _S1, 2 * _S1) is False
+    # Idempotency: a second install call must not wrap the wrapper.
+    patch_module._patch_inductor_factorable_divisibility()
+    assert SizeVarAllocator.statically_known_multiple_of is method