wan_moe_i2v_distill_quant.json

{
    "infer_steps": 4,
    "target_video_length": 81,
    "text_len": 512,
    "target_height": 480,
    "target_width": 832,
    "self_attn_1_type": "flash_attn3",
    "cross_attn_1_type": "flash_attn3",
    "cross_attn_2_type": "flash_attn3",
    "seed": 42,
    "sample_guide_scale": [3.5, 3.5],
    "sample_shift": 5.0,
    "enable_cfg": false,
    "cpu_offload": true,
    "offload_granularity": "model",
    "t5_cpu_offload": false,
    "vae_cpu_offload": false,
    "use_image_encoder": false,
    "boundary_step_index": 2,
    "denoising_step_list": [1000, 750, 500, 250],
    "mm_config": {
        "mm_type": "W-int8-channel-sym-A-int8-channel-sym-dynamic-Vllm"
    },
    "t5_quantized": true,
    "t5_quant_scheme": "int8"
}