[Diffusion] Document DLO mmap model opt-in
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
1 parent
76e257b0f3
commit
1c3d59796f
3 files changed
+31
-4
No files matched your search
@@ -532,9 +532,11 @@ class MiniMaxH3Pipeline(
|
||||
encoder_block_attrs={"text_encoder": ("vision.blocks", "text_model.layers")},
|
||||
on_demand_component_paths=frozenset({"text_encoder", "video_vae", "audio_vae"}),
|
||||
)
|
||||
# TP1 DLO mmap applies the grouped-QKV adapter while packing each block.
|
||||
# The fused MLP checkpoint is already gate-then-up, matching its TP1
|
||||
# runtime layout. TP>1 and quantized layouts stay on the regular loader.
|
||||
# Explicit mmap opt-in: weights_sources below provide exact pipeline
|
||||
# prefixes, and TP1 DLO mmap applies the grouped-QKV adapter while packing
|
||||
# each block. The fused MLP checkpoint is already gate-then-up, matching
|
||||
# its TP1 runtime layout. TP>1 and quantized layouts stay on the regular
|
||||
# loader. See the DLO design doc for the model opt-in contract.
|
||||
_supports_mmap_loading: ClassVar[bool] = True
|
||||
_PROFILER_TARGETS: ClassVar[list[str]] = [
|
||||
"_prepare_reference_videos",
|
||||
|
||||
Reference in new issue
Block a user