[Core][Diffusion] Camera interaction for diffusion streaming generation (LingBot World 2 as example) (#7198)

Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
This commit is contained in:
Zeyu Huang | 黃澤宇 authored and GitHub committed 2026-09-20 16:19:41 +00:00
1 parent 139a47a578
commit e36babd48f
26 files changed
+2071 -200

No files matched your search

+5 -1
View File
@@ -5,12 +5,13 @@ A pipeline only declares the modalities that it supports.
And a pipeline can choose which handler for each modality (there can be more than one handler for a modality).
Outer key: pipeline architecture name (``od_config.model_class_name``).
Inner key: modality name (e.g. ``\"prompt\"``).
Inner key: modality name (e.g. ``\"camera\"``).
"""
from __future__ import annotations
from vllm_omni.diffusion.interaction.modality_handlers.base import InteractionHandler
from vllm_omni.diffusion.interaction.modality_handlers.camera import SE3DeltaCameraHandler
from vllm_omni.diffusion.interaction.modality_handlers.prompt import PromptInteractionHandler
STRUCTURED_HANDLER_REGISTRY: dict[str, dict[str, type[InteractionHandler]]] = {
@@ -21,4 +22,7 @@ STRUCTURED_HANDLER_REGISTRY: dict[str, dict[str, type[InteractionHandler]]] = {
"HeliosPyramidPipeline": {
"prompt": PromptInteractionHandler,
},
"LingBotWorldCausalDMDPipeline": {
"camera": SE3DeltaCameraHandler,
},
}