[Diffusion] Add Minimax-H3 modular pipeline support (#5720)

Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: David Chen <530634352@qq.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: David Chen <530634352@qq.com>
This commit is contained in:
authored and GitHub committed 2026-08-06 11:43:23 +00:00
1 parent d219d93bbb
commit 48298030d4
25 files changed
+843 -177

No files matched your search

+31 -5
View File
@@ -86,9 +86,35 @@ class TestCacheDiTBackend:
# Verify cache-dit was enabled
assert backend.enabled is True
assert backend._refresh_func is not None
assert backend._refresh_funcs
mock_cache_dit.enable_cache.assert_called_once()
@patch("vllm_omni.diffusion.cache.cachedit.backend.BlockAdapter")
@patch("vllm_omni.diffusion.cache.cachedit.backend.cache_dit")
def test_enable_and_refresh_every_declared_dit(self, mock_cache_dit, mock_block_adapter):
"""Combined pipelines enable and refresh Cache-DiT for every DiT."""
pipeline = Mock()
pipeline.__class__.__name__ = "MiniMaxH3Pipeline"
pipeline._dit_modules = ["transformer", "transformers_ref"]
pipeline.transformer = Mock()
pipeline.transformers_ref = Mock()
for transformer in (pipeline.transformer, pipeline.transformers_ref):
transformer._cache_dit_adapter_config = CacheDiTAdapterConfig(
block_forward_patterns={"blocks": ForwardPattern.Pattern_3}
)
backend = CacheDiTBackend({"Fn_compute_blocks": 2})
backend.enable(pipeline)
backend.refresh(pipeline, num_inference_steps=20)
assert len(backend._refresh_funcs) == 2
assert mock_cache_dit.enable_cache.call_count == 2
assert mock_cache_dit.refresh_context.call_count == 2
assert {call.args[0] for call in mock_cache_dit.refresh_context.call_args_list} == {
pipeline.transformer,
pipeline.transformers_ref,
}
@patch("vllm_omni.diffusion.cache.cachedit.backend.logger")
@patch("vllm_omni.diffusion.cache.cachedit.backend.cache_dit")
def test_enable_without_model_adapter_uses_cache_dit_registry(self, mock_cache_dit, mock_logger):
@@ -106,7 +132,7 @@ class TestCacheDiTBackend:
backend.enable(pipeline)
assert backend.enabled is True
assert backend._refresh_func is not None
assert backend._refresh_funcs
assert mock_cache_dit.enable_cache.call_args.args[0] is pipeline.transformer
mock_logger.info.assert_any_call(
"Transformer %s does not declare _cache_dit_adapter_config; "
@@ -138,7 +164,7 @@ class TestCacheDiTBackend:
assert isinstance(exc_info.value.__cause__, ValueError)
assert backend.enabled is False
assert backend._refresh_func is None
assert backend._refresh_funcs == []
@patch("vllm_omni.diffusion.cache.cachedit.backend.BlockAdapter")
@patch("vllm_omni.diffusion.cache.cachedit.backend.cache_dit")
@@ -245,7 +271,7 @@ class TestCacheDiTBackend:
backend.enable(mock_pipeline)
assert backend.enabled is True
assert backend._refresh_func is not None
assert backend._refresh_funcs
mock_block_adapter.assert_called_once()
adapter_kwargs = mock_block_adapter.call_args.kwargs
assert adapter_kwargs["transformer"] is mock_pipeline.model
@@ -285,7 +311,7 @@ class TestCacheDiTBackend:
backend.enable(mock_pipeline)
assert backend.enabled is True
assert backend._refresh_func is not None
assert backend._refresh_funcs
mock_block_adapter.assert_called_once()
adapter_kwargs = mock_block_adapter.call_args.kwargs
assert adapter_kwargs["transformer"] is mock_pipeline.transformer