Files
vllm-omni/vllm_omni/deploy/mammoth_moda2.yaml
T
7b4fc7ce2e [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>
2026-09-18 13:29:18 -07:00

23 lines
461 B
YAML

# MammothModa2 AR→DiT (text-to-image).
async_chunk: false
pipeline: mammoth_moda2
stages:
- stage_id: 0
devices: "0"
max_num_seqs: 100
max_model_len: 8192
gpu_memory_utilization: 0.5
enforce_eager: true
trust_remote_code: true
enable_prefix_caching: false
- stage_id: 1
devices: "0"
max_num_seqs: 1
gpu_memory_utilization: 0.3
enforce_eager: true
trust_remote_code: true
enable_prefix_caching: false