modelopt-v3/_nvfp4_qcfg_debug.json

{
  "quant_cfg": {
    "*weight_quantizer": {
      "num_bits": [
        2,
        1
      ],
      "block_sizes": {
        "-1": 16,
        "type": "dynamic",
        "scale_bits": [
          4,
          3
        ]
      },
      "enable": true
    },
    "*input_quantizer": {
      "enable": false
    },
    "nn.BatchNorm1d": {
      "*": {
        "enable": false
      }
    },
    "nn.BatchNorm2d": {
      "*": {
        "enable": false
      }
    },
    "nn.BatchNorm3d": {
      "*": {
        "enable": false
      }
    },
    "nn.LeakyReLU": {
      "*": {
        "enable": false
      }
    },
    "*lm_head*": {
      "enable": false
    },
    "*proj_out.*": {
      "enable": false
    },
    "*block_sparse_moe.gate*": {
      "enable": false
    },
    "*router*": {
      "enable": false
    },
    "*mlp.gate.*": {
      "enable": false
    },
    "*mlp.shared_expert_gate.*": {
      "enable": false
    },
    "*linear_attn.conv1d*": {
      "enable": false
    },
    "*mixer.conv1d*": {
      "enable": false
    },
    "*output_layer*": {
      "enable": false
    },
    "output.*": {
      "enable": false
    },
    "default": {
      "enable": false
    },
    "*embed_tokens*": {
      "enable": false
    },
    "*norm*": {
      "enable": false
    },
    "*layernorm*": {
      "enable": false
    },
    "*LayerNorm*": {
      "enable": false
    },
    "*rotary*": {
      "enable": false
    },
    "*pos_embed*": {
      "enable": false
    },
    "*patch_embed*": {
      "enable": false
    },
    "*bias*": {
      "enable": false
    },
    "*final_layer2*": {
      "enable": false
    },
    "*t_embedder1*": {
      "enable": false
    },
    "*x_embedder*": {
      "enable": false
    },
    "*visual*": {
      "enable": false
    },
    "*visual.*": {
      "enable": false
    },
    "model.visual*": {
      "enable": false
    },
    "model.visual.*": {
      "enable": false
    },
    "*model.visual*": {
      "enable": false
    },
    "*model.visual.*": {
      "enable": false
    },
    "*visual*weight_quantizer": {
      "enable": false
    },
    "*visual*input_quantizer": {
      "enable": false
    },
    "model.visual*weight_quantizer": {
      "enable": false
    },
    "model.visual*input_quantizer": {
      "enable": false
    },
    "*visual.blocks*": {
      "enable": false
    },
    "*visual.blocks.*": {
      "enable": false
    },
    "*visual.blocks.*.attn.qkv*": {
      "enable": false
    }
  },
  "algorithm": null
}