# Lance-3B (ByteDance) deploy — single-stage, CUDA. Target: 1x NVIDIA A100 80GB. # # Lance is BAGEL-lineage (Qwen2-MoT unified AR+diffusion). The single-stage # DiT stage is self-contained: it owns the Qwen2-MoT LLM, the Qwen2.5-VL ViT, # the Wan2.2 VAE and the tokenizer (text2img / image_edit / x2t_image). # # Lance-3B BF16 footprint: ~7GB LLM + Qwen2.5-VL ViT + Wan2.2 VAE — comfortably # within one A100 80GB. The video checkpoint (Lance_3B_Video) is a follow-up. # # Select via: # vllm serve bytedance-research/Lance --omni \ # --deploy-config vllm_omni/deploy/lance.yaml # or programmatically: # Omni(model="bytedance-research/Lance", # deploy_config_path="vllm_omni/deploy/lance.yaml") pipeline: lance async_chunk: false stages: - stage_id: 0 max_num_batched_tokens: 32768 max_num_seqs: 1 enforce_eager: true trust_remote_code: true enable_prefix_caching: false devices: "0" default_sampling_params: seed: 42