[BugFix] Fix MammothModa2 Text-to-Image Bug (#4299)

Signed-off-by: menjiantong <menjiantong@foxmail.com>
Co-authored-by: menjiantong <menjiantong@foxmail.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
This commit is contained in:
authored and GitHub committed 2026-06-25 13:14:02 +08:00
1 parent 0d0f4e669e
commit 0fd2620d56
4 files changed
+116 -5

No files matched your search

@@ -11,12 +11,16 @@ from vllm_omni.inputs.data import OmniTokensPrompt
def ar2dit(
source_outputs: list[Any],
prompts: OmniTokensPrompt | TextPrompt | None = None,
prompts: OmniTokensPrompt | TextPrompt | list[OmniTokensPrompt | TextPrompt] | None = None,
_requires_multimodal_data: bool = False,
) -> list[OmniTokensPrompt]:
"""Convert AR stage outputs to DiT stage inputs."""
ar_outputs = source_outputs
# Normalize prompts to list
if not isinstance(prompts, list):
prompts = [prompts] if prompts is not None else [{}]
dit_inputs: list[OmniTokensPrompt] = []
for ar_output, prompt in zip(ar_outputs, prompts):
addi_info = prompt["additional_information"]