[Model] Migrate MammothModa2 DiT to the shared diffusion runtime (#7134)

Signed-off-by: levius <2114377220@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
This commit is contained in:
authored and GitHub committed 2026-09-18 13:29:18 -07:00
1 parent ca3ccfc9a3
commit 7b4fc7ce2e
16 files changed
+1046 -427

No files matched your search

@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""MammothModa2 pipeline topology (frozen).
Stage 0: AR — multimodal understanding + latent generation
@@ -8,6 +8,7 @@ Stage 1: DiT — latent → image
For text/image understanding tasks (text output only), use MAMMOTH_MODA2_AR_PIPELINE.
"""
from vllm_omni.config.endpoint_policy import EndpointRestriction, OmniServingCapability
from vllm_omni.config.stage_config import (
PipelineConfig,
StageExecutionType,
@@ -21,6 +22,13 @@ MAMMOTH_MODA2_PIPELINE = PipelineConfig(
default_deploy_config_name="mammoth_moda2.yaml",
model_arch="MammothModa2ForConditionalGeneration",
hf_architectures=("Mammothmoda2Model", "MammothModa2ForConditionalGeneration"),
endpoint_restrictions=(
EndpointRestriction(
OmniServingCapability.IMAGE_EDITS,
"MammothModa2 image editing (img2img) is not supported. "
"Use /v1/images/generations for text-to-image requests.",
),
),
stages=(
StagePipelineConfig(
stage_id=0,
@@ -35,14 +43,15 @@ MAMMOTH_MODA2_PIPELINE = PipelineConfig(
StagePipelineConfig(
stage_id=1,
model_stage="dit",
execution_type=StageExecutionType.LLM_GENERATION,
execution_type=StageExecutionType.DIFFUSION,
input_sources=(0,),
final_output=True,
final_output_type="image",
owns_tokenizer=False,
requires_multimodal_data=False,
engine_output_type="image",
custom_process_input_func=f"{_PROC}.ar2dit",
model_arch="MammothModa2DiTPipeline",
custom_process_input_func=f"{_PROC}.ar2diffusion",
omni_kv_config={"need_recv_cache": False},
),
),
)
@@ -142,11 +142,6 @@ _OMNI_MODELS = {
"mammoth_moda2",
"MammothModa2Qwen3ForCausalLM",
),
"MammothModa2DiTPipeline": (
"mammoth_moda2",
"pipeline_mammothmoda2_dit",
"MammothModa2DiTPipeline",
),
"MammothModa2ForConditionalGeneration": (
"mammoth_moda2",
"mammoth_moda2",