[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Luka Govedič
2026-05-01 23:41:15 -04:00
committed by GitHub
parent 3e49479c4b
commit d58c42e19c
44 changed files with 2833 additions and 779 deletions
@@ -23,11 +23,7 @@ from vllm.model_executor.layers.fused_moe.router.fused_topk_router import (
vllm_topk_sigmoid,
vllm_topk_softmax,
)
from vllm.model_executor.layers.layernorm import (
RMSNorm,
dispatch_rocm_rmsnorm_func,
fused_add_rms_norm,
)
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.platforms import current_platform
RMS_NORM_SUPPORTED_DTYPES = [torch.float16, torch.bfloat16]
@@ -153,26 +149,3 @@ def test_topk_sigmoid_dispatch(use_rocm_aiter: bool):
assert topk_func == rocm_aiter_ops.topk_sigmoid
else:
assert topk_func == vllm_topk_sigmoid
@pytest.mark.parametrize("add_residual", [False])
@pytest.mark.parametrize("dtype", [torch.float32, torch.float16, torch.bfloat16])
@pytest.mark.parametrize("use_rocm_aiter", [True, False])
@pytest.mark.skipif(
not current_platform.is_rocm(), reason="AITER is a feature exclusive for ROCm"
)
def test_rms_norm_dispatch(
add_residual: bool, dtype: torch.dtype, use_rocm_aiter: bool
):
rms_norm_func = dispatch_rocm_rmsnorm_func(dtype, use_rocm_aiter)
should_use_rocm_aiter = (
current_platform.is_rocm()
and use_rocm_aiter
and dtype in RMS_NORM_SUPPORTED_DTYPES
)
if should_use_rocm_aiter:
assert rms_norm_func == rocm_aiter_ops.rms_norm2d_with_add
else:
assert rms_norm_func == fused_add_rms_norm
+78 -41
View File
@@ -1,60 +1,97 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import multiprocessing
import types
import pytest
import torch
from vllm.platforms import current_platform
def _load_oink_ops_module():
# Import the module normally (vllm is installed as an editable package in CI).
from vllm import _oink_ops
def _test_oink_availability_impl(
device_capability: tuple[int, int],
has_rmsnorm: bool,
has_fused_add_rms_norm: bool,
expected_available: bool,
expected_fused: bool,
) -> None:
"""Test OINK support detection with mocked state."""
import torch
return _oink_ops
from vllm import platforms
# Mock device capability (class method, override on class)
dc = platforms.interface.DeviceCapability(*device_capability)
platforms.current_platform.__class__.get_device_capability = lambda device_id=0: dc
# Mock oink ops
oink_ops = types.SimpleNamespace()
if has_rmsnorm:
oink_ops.rmsnorm = lambda x, w, eps: x
if has_fused_add_rms_norm:
oink_ops.fused_add_rms_norm = lambda x, residual, w, eps: None
torch.ops.oink = oink_ops
# Now import vllm modules with mocks in place (fresh import with mocked platform)
import vllm.kernels.oink_ops # noqa: F401
from vllm.ir.ops import fused_add_rms_norm, rms_norm
# Verify support checks
assert rms_norm.impls["oink"].supported is expected_available
assert fused_add_rms_norm.impls["oink"].supported is expected_fused
def test_oink_availability_checks(monkeypatch: pytest.MonkeyPatch):
_oink_ops = _load_oink_ops_module()
@pytest.mark.parametrize(
"device_capability,has_rmsnorm,has_fused_add_rms_norm,expected_available,expected_fused",
[
# Case 1: < SM100, ops not supported
((9, 0), True, False, False, False),
# Case 2: CUDA available and SM100, rmsnorm op registered
((10, 0), True, False, True, False),
# Case 3: SM100 with both rmsnorm and fused_add_rms_norm
((10, 0), True, True, True, True),
],
)
@pytest.mark.skipif(not current_platform.is_cuda(), reason="Only test on CUDA")
def test_oink_availability_checks(
device_capability: tuple[int, int],
has_rmsnorm: bool,
has_fused_add_rms_norm: bool,
expected_available: bool,
expected_fused: bool,
):
"""Test OINK support detection with clean import state for each parameter set."""
# Ensure the ops namespace exists and is mutable for tests.
monkeypatch.setattr(
torch.ops,
"oink",
types.SimpleNamespace(rmsnorm=lambda x, w, eps: x),
raising=False,
)
# Case 1: CUDA not available.
monkeypatch.setattr(torch.cuda, "is_available", lambda: False)
assert _oink_ops.is_oink_available_for_device(0) is False
# Case 2: CUDA available but < SM100.
monkeypatch.setattr(torch.cuda, "is_available", lambda: True)
monkeypatch.setattr(torch.cuda, "get_device_capability", lambda idx: (9, 0))
assert _oink_ops.is_oink_available_for_device(0) is False
# Case 3: CUDA available and SM100, rmsnorm op registered.
monkeypatch.setattr(torch.cuda, "get_device_capability", lambda idx: (10, 0))
assert _oink_ops.is_oink_available_for_device(0) is True
# fused op presence probe
assert _oink_ops.has_fused_add_rms_norm() is False
monkeypatch.setattr(
torch.ops,
"oink",
types.SimpleNamespace(
rmsnorm=lambda x, w, eps: x,
fused_add_rms_norm=lambda x, residual, w, eps: None,
# Use spawn to run function in fresh process with clean imports
# TODO migrate to spawn utility:
# https://github.com/vllm-project/vllm/issues/41415
ctx = multiprocessing.get_context("spawn")
process = ctx.Process(
target=_test_oink_availability_impl,
args=(
device_capability,
has_rmsnorm,
has_fused_add_rms_norm,
expected_available,
expected_fused,
),
raising=False,
)
assert _oink_ops.has_fused_add_rms_norm() is True
process.start()
process.join()
if process.exitcode != 0:
raise AssertionError(
f"Subprocess test failed with exit code {process.exitcode}"
)
def test_can_view_as_2d_stride_guard():
# Import the helper from the layernorm module.
from vllm.model_executor.layers.layernorm import _can_view_as_2d
# No global import
import torch
# Import the helper from the kernels module.
from vllm.kernels.oink_ops import _can_view_as_2d
x = torch.zeros((2, 3, 4))
assert _can_view_as_2d(x) is True