smash_config.json

{
    "batcher": null,
    "cacher": null,
    "compiler": "torch_compile",
    "factorizer": null,
    "pruner": null,
    "quantizer": "hqq_diffusers",
    "hqq_diffusers_backend": "torchao_int4",
    "hqq_diffusers_group_size": 64,
    "hqq_diffusers_weight_bits": 8,
    "torch_compile_backend": "inductor",
    "torch_compile_dynamic": null,
    "torch_compile_fullgraph": true,
    "torch_compile_make_portable": false,
    "torch_compile_max_kv_cache_size": 400,
    "torch_compile_mode": "max-autotune",
    "torch_compile_seqlen_manual_cuda_graph": 100,
    "torch_compile_target": "model",
    "batch_size": 1,
    "device": "cuda",
    "save_fns": [
        "hqq_diffusers",
        "save_before_apply"
    ],
    "load_fns": [
        "hqq_diffusers"
    ],
    "reapply_after_load": {
        "factorizer": null,
        "pruner": null,
        "quantizer": null,
        "cacher": null,
        "compiler": "torch_compile",
        "batcher": null
    }
}