[Perf] Minimax-H3 support fused RMSNorm and RoPE opt (#5801)

Signed-off-by: Fan <fan@FandeMacBook-Air.local>
Co-authored-by: Fan <fan@FandeMacBook-Air.local>

tests/diffusion/layers/test_norm.py

@@ -2,6 +2,9 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Unit tests for LayerNorm and RMSNorm custom ops in diffusion layers."""
 
+import sys
+import types
+
 import pytest
 import torch
 from pytest_mock import MockerFixture
@@ -299,6 +302,44 @@ def test_rmsnorm_numerical_correctness():
     torch.testing.assert_close(out, expected, atol=1e-5, rtol=1e-5)
 
 
+def test_rmsnorm_dtype_matches_parameter_and_fp32_accumulation_contract():
+    """dtype controls gamma storage; reduced-precision inputs still use fp32 accumulation."""
+    from vllm_omni.diffusion.layers.norm import RMSNorm
+
+    hidden_size = 64
+    eps = 1e-6
+    norm = RMSNorm(hidden_size, eps=eps, dtype=torch.bfloat16)
+    x = torch.randn(2, 4, hidden_size, dtype=torch.bfloat16)
+
+    assert norm.weight.dtype == torch.bfloat16
+
+    x_fp32 = x.float()
+    expected = (x_fp32 * torch.rsqrt(x_fp32.square().mean(-1, keepdim=True) + eps) * norm.weight.float()).to(x.dtype)
+
+    torch.testing.assert_close(norm.forward_native(x), expected, atol=0, rtol=0)
+
+
+def test_rmsnorm_npu_receives_gamma_with_configured_dtype(monkeypatch: pytest.MonkeyPatch):
+    """The NPU fused op receives the bf16 checkpoint gamma used by H3."""
+    from vllm_omni.diffusion.layers.norm import RMSNorm
+
+    captured: dict[str, torch.Tensor] = {}
+
+    def npu_rms_norm(x: torch.Tensor, gamma: torch.Tensor, epsilon: float):
+        captured["gamma"] = gamma
+        captured["epsilon"] = torch.tensor(epsilon)
+        return (x,)
+
+    monkeypatch.setitem(sys.modules, "torch_npu", types.SimpleNamespace(npu_rms_norm=npu_rms_norm))
+    norm = RMSNorm(64, eps=1e-5, dtype=torch.bfloat16)
+    x = torch.randn(2, 4, 64, dtype=torch.bfloat16)
+
+    assert norm.forward_npu(x) is x
+    assert captured["gamma"] is norm.weight
+    assert captured["gamma"].dtype == torch.bfloat16
+    assert captured["epsilon"].item() == pytest.approx(1e-5)
+
+
 # ── RMSNorm compile-path regression tests ──
 
 

tests/diffusion/layers/test_rope_broadcast.py

@@ -10,10 +10,13 @@ forward_hip, and apply_rotary_emb_mindiesd paths.
 
 from __future__ import annotations
 
+import sys
+import types
+
 import pytest
 import torch
 
-from vllm_omni.diffusion.layers.rope import RotaryEmbedding
+from vllm_omni.diffusion.layers.rope import RotaryEmbedding, apply_rotary_emb_mindiesd
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 
@@ -234,3 +237,33 @@ class TestRotaryEmbeddingNativeShapeRegression:
         output = rope.forward_native(x, cos, sin)
         assert output.shape == x.shape
         assert not torch.isnan(output).any()
+
+
+def test_mindie_full_dim_rope_keeps_h3_cos_sin_layout(monkeypatch: pytest.MonkeyPatch) -> None:
+    """H3 passes complete rotary dims to MindIE instead of the CUDA half-dim layout."""
+    captured: dict[str, object] = {}
+
+    def rotary_position_embedding(x, cos, sin, **kwargs):
+        captured.update(x=x, cos=cos, sin=sin, kwargs=kwargs)
+        return x
+
+    monkeypatch.setitem(
+        sys.modules,
+        "mindiesd",
+        types.SimpleNamespace(rotary_position_embedding=rotary_position_embedding),
+    )
+    x = torch.randn(11, 3, 96, dtype=torch.bfloat16)
+    cos = torch.randn(11, 96, dtype=torch.bfloat16)
+    sin = torch.randn(11, 96, dtype=torch.bfloat16)
+
+    actual = apply_rotary_emb_mindiesd(x, cos, sin, interleaved=False, half_head_dim=False)
+
+    assert actual is x
+    assert captured["x"] is x
+    assert captured["cos"] is cos
+    assert captured["sin"] is sin
+    assert captured["kwargs"] == {
+        "rotated_mode": "rotated_half",
+        "head_first": False,
+        "fused": True,
+    }