[Bugfix][Diffusion] Preserve stage attention backend (#6645)

Signed-off-by: AndyZhou952 <jzhoubc@connect.ust.hk>
This commit is contained in:
Andy Zhou authored and GitHub committed 2026-09-01 20:18:44 +08:00
1 parent d1c8beeb18
commit 2298359f67
7 files changed
+184 -7

No files matched your search

@@ -11,7 +11,7 @@ import types
import pytest
from vllm_omni.diffusion.data import AttentionConfig, AttentionSpec
from vllm_omni.diffusion.data import AttentionConfig, AttentionSpec, normalize_omni_diffusion_kwargs
from vllm_omni.engine import async_omni_engine as async_omni_engine_module
from vllm_omni.engine.async_omni_engine import AsyncOmniEngine
from vllm_omni.engine.stage_init_utils import (
@@ -1795,6 +1795,41 @@ def test_resolve_stage_configs_preserves_stage_diffusion_attention(monkeypatch):
assert stage_configs[0].engine_args.diffusion_attention_config is existing_attention
def test_resolve_stage_configs_does_not_inject_over_stage_diffusion_attention_backend(monkeypatch):
import vllm_omni.engine.async_omni_engine as engine_mod
engine = object.__new__(AsyncOmniEngine)
stage_cfg = types.SimpleNamespace(
stage_type="diffusion",
engine_args=types.SimpleNamespace(
diffusion_attention_backend="TORCH_SDPA",
diffusion_attention_config=None,
lora_path=None,
lora_scale=None,
enable_sleep_mode=None,
quantization_config=None,
),
)
monkeypatch.setattr(
engine_mod,
"load_and_resolve_stage_configs",
lambda *args, **kwargs: ("dummy-config", [stage_cfg], None),
)
_config_path, stage_configs = engine._resolve_stage_configs(
model="dummy-model",
kwargs={"diffusion_attention_backend": "FLASH_ATTN"},
trust_remote_code=False,
)
engine_args = stage_configs[0].engine_args
assert engine_args.diffusion_attention_backend == "TORCH_SDPA"
assert engine_args.diffusion_attention_config is None
normalized = normalize_omni_diffusion_kwargs(vars(engine_args))
assert normalized["diffusion_attention_config"].default.backend == "TORCH_SDPA"
def test_resolve_stage_configs_does_not_inject_diffusion_attention_into_llm_stage(monkeypatch):
import vllm_omni.engine.async_omni_engine as engine_mod
+58 -1
View File
@@ -133,7 +133,7 @@ def _stable_engine_arg_environment(monkeypatch, tmp_path):
for worker_type in ("ar", "generation"):
worker_module = types.ModuleType(f"test.{worker_type}")
worker_module.Worker = _TestWorker
setattr(worker_module, "Worker", _TestWorker)
monkeypatch.setitem(sys.modules, worker_module.__name__, worker_module)
@@ -434,6 +434,63 @@ def test_typed_diffusion_engine_args_use_structured_diffusion_config(tmp_path):
assert typed_args["diffusion_attention_config"].per_role["cross"].backend == "TORCH_SDPA"
def test_engine_args_consume_stage_diffusion_attention_shorthand(tmp_path):
"""A stage-level ``diffusion_attention_backend`` shorthand is folded into the structured config."""
pipeline, deploy, model = _engine_arg_inputs(tmp_path)
deploy.stages[2] = replace(
deploy.stages[2],
diffusion_attention_config=None,
diffusion_attention_backend="TORCH_SDPA",
)
legacy_stages, omni_config = _legacy_and_typed_stages(pipeline, deploy, model)
legacy_args = build_legacy_engine_args_dict(legacy_stages[2], model)
typed_args = build_engine_args_dict_from_omni_stage_config(
omni_config.stage_by_id(2),
model,
)
for engine_args in (legacy_args, typed_args):
assert engine_args.get("diffusion_attention_backend") is None
assert isinstance(engine_args["diffusion_attention_config"], AttentionConfig)
assert engine_args["diffusion_attention_config"].default.backend == "TORCH_SDPA"
od_config = OmniDiffusionConfig.from_kwargs(**engine_args)
assert od_config.diffusion_attention_config.default.backend == "TORCH_SDPA"
@pytest.mark.parametrize(
"yaml_attention_config",
[
{"default": {"backend": "FLASH_ATTN"}, "per_role": {"cross": {"backend": "SAGE_ATTN"}}},
{"per_role": {"cross": {"backend": "SAGE_ATTN"}}},
],
ids=["yaml-default", "yaml-per-role-only"],
)
def test_engine_args_apply_cli_attention_shorthand_over_yaml_config(tmp_path, yaml_attention_config):
pipeline, deploy, model = _engine_arg_inputs(tmp_path)
deploy.stages[2] = replace(deploy.stages[2], diffusion_attention_config=yaml_attention_config)
legacy_stages, omni_config = _legacy_and_typed_stages(
pipeline,
deploy,
model,
cli_overrides={"stage_2_diffusion_attention_backend": "TORCH_SDPA"},
)
legacy_args = build_legacy_engine_args_dict(legacy_stages[2], model)
typed_args = build_engine_args_dict_from_omni_stage_config(
omni_config.stage_by_id(2),
model,
)
for engine_args in (legacy_args, typed_args):
assert engine_args.get("diffusion_attention_backend") is None
attention_config = engine_args["diffusion_attention_config"]
assert attention_config.default.backend == "TORCH_SDPA"
assert attention_config.per_role["cross"].backend == "SAGE_ATTN"
od_config = OmniDiffusionConfig.from_kwargs(**engine_args)
assert od_config.diffusion_attention_config.default.backend == "TORCH_SDPA"
def test_typed_engine_args_preserve_explicit_backend_default_overrides(tmp_path):
pipeline, deploy, model = _engine_arg_inputs(tmp_path)
deploy.enable_prefix_caching = False