{ "quantization": { "quant_algo": "NVFP4", "kv_cache_quant_algo": "none", "exclude_modules": [ "model.audio.encoder", "model.audio.final_norm", "model.llm.embed", "model.llm.embed_norm", "model.llm.norm", "model.llm.unembed", "model.visual.final_norm", "model.visual.layers.linear_0", "model.visual.layers.linear_1", "model.visual.layers.linear_2", "model.visual.layers.linear_3", "model.visual.layers.norm_0", "model.visual.layers.norm_1", "model.visual.layers.norm_2", "model.llm.layers.0.attn", "model.llm.layers.0.attn_norm", "model.llm.layers.0.attn_sconv", "model.llm.layers.0.mlp.global_scale", "model.llm.layers.0.mlp.w13_dn", "model.llm.layers.0.mlp.w2_md", "model.llm.layers.0.mlp_norm", "model.llm.layers.0.mlp_sconv", "model.llm.layers.1.attn", "model.llm.layers.1.attn_norm", "model.llm.layers.1.attn_sconv", "model.llm.layers.1.mlp.global_scale", "model.llm.layers.1.mlp.w13_dn", "model.llm.layers.1.mlp.w2_md", "model.llm.layers.1.mlp_norm", "model.llm.layers.1.mlp_sconv", "model.llm.layers.10.attn", "model.llm.layers.10.attn_norm", "model.llm.layers.10.attn_sconv", "model.llm.layers.10.mlp.gate", "model.llm.layers.10.mlp.shared_experts", "model.llm.layers.10.mlp_norm", "model.llm.layers.10.mlp_sconv", "model.llm.layers.11.attn", "model.llm.layers.11.attn_norm", "model.llm.layers.11.attn_sconv", "model.llm.layers.11.mlp.gate", "model.llm.layers.11.mlp.shared_experts", "model.llm.layers.11.mlp_norm", "model.llm.layers.11.mlp_sconv", "model.llm.layers.12.attn", "model.llm.layers.12.attn_norm", "model.llm.layers.12.attn_sconv", "model.llm.layers.12.mlp.gate", "model.llm.layers.12.mlp.shared_experts", "model.llm.layers.12.mlp_norm", "model.llm.layers.12.mlp_sconv", "model.llm.layers.13.attn", "model.llm.layers.13.attn_norm", "model.llm.layers.13.attn_sconv", "model.llm.layers.13.mlp.gate", "model.llm.layers.13.mlp.shared_experts", "model.llm.layers.13.mlp_norm", "model.llm.layers.13.mlp_sconv", "model.llm.layers.14.attn", "model.llm.layers.14.attn_norm", "model.llm.layers.14.attn_sconv", "model.llm.layers.14.mlp.gate", "model.llm.layers.14.mlp.shared_experts", "model.llm.layers.14.mlp_norm", "model.llm.layers.14.mlp_sconv", "model.llm.layers.15.attn", "model.llm.layers.15.attn_norm", "model.llm.layers.15.attn_sconv", "model.llm.layers.15.mlp.gate", "model.llm.layers.15.mlp.shared_experts", "model.llm.layers.15.mlp_norm", "model.llm.layers.15.mlp_sconv", "model.llm.layers.16.attn", "model.llm.layers.16.attn_norm", "model.llm.layers.16.attn_sconv", "model.llm.layers.16.mlp.gate", "model.llm.layers.16.mlp.shared_experts", "model.llm.layers.16.mlp_norm", "model.llm.layers.16.mlp_sconv", "model.llm.layers.17.attn", "model.llm.layers.17.attn_norm", "model.llm.layers.17.attn_sconv", "model.llm.layers.17.mlp.gate", "model.llm.layers.17.mlp.shared_experts", "model.llm.layers.17.mlp_norm", "model.llm.layers.17.mlp_sconv", "model.llm.layers.18.attn", "model.llm.layers.18.attn_norm", "model.llm.layers.18.attn_sconv", "model.llm.layers.18.mlp.gate", "model.llm.layers.18.mlp.shared_experts", "model.llm.layers.18.mlp_norm", "model.llm.layers.18.mlp_sconv", "model.llm.layers.19.attn", "model.llm.layers.19.attn_norm", "model.llm.layers.19.attn_sconv", "model.llm.layers.19.mlp.gate", "model.llm.layers.19.mlp.shared_experts", "model.llm.layers.19.mlp_norm", "model.llm.layers.19.mlp_sconv", "model.llm.layers.2.attn", "model.llm.layers.2.attn_norm", "model.llm.layers.2.attn_sconv", "model.llm.layers.2.mlp.experts", "model.llm.layers.2.mlp.gate", "model.llm.layers.2.mlp.shared_experts", "model.llm.layers.2.mlp_norm", "model.llm.layers.2.mlp_sconv", "model.llm.layers.20.attn", "model.llm.layers.20.attn_norm", "model.llm.layers.20.attn_sconv", "model.llm.layers.20.mlp.gate", "model.llm.layers.20.mlp.shared_experts", "model.llm.layers.20.mlp_norm", "model.llm.layers.20.mlp_sconv", "model.llm.layers.21.attn", "model.llm.layers.21.attn_norm", "model.llm.layers.21.attn_sconv", "model.llm.layers.21.mlp.gate", "model.llm.layers.21.mlp.shared_experts", "model.llm.layers.21.mlp_norm", "model.llm.layers.21.mlp_sconv", "model.llm.layers.22.attn", "model.llm.layers.22.attn_norm", "model.llm.layers.22.attn_sconv", "model.llm.layers.22.mlp.gate", "model.llm.layers.22.mlp.shared_experts", "model.llm.layers.22.mlp_norm", "model.llm.layers.22.mlp_sconv", "model.llm.layers.23.attn", "model.llm.layers.23.attn_norm", "model.llm.layers.23.attn_sconv", "model.llm.layers.23.mlp.gate", "model.llm.layers.23.mlp.shared_experts", "model.llm.layers.23.mlp_norm", "model.llm.layers.23.mlp_sconv", "model.llm.layers.24.attn", "model.llm.layers.24.attn_norm", "model.llm.layers.24.attn_sconv", "model.llm.layers.24.mlp.gate", "model.llm.layers.24.mlp.shared_experts", "model.llm.layers.24.mlp_norm", "model.llm.layers.24.mlp_sconv", "model.llm.layers.25.attn", "model.llm.layers.25.attn_norm", "model.llm.layers.25.attn_sconv", "model.llm.layers.25.mlp.gate", "model.llm.layers.25.mlp.shared_experts", "model.llm.layers.25.mlp_norm", "model.llm.layers.25.mlp_sconv", "model.llm.layers.26.attn", "model.llm.layers.26.attn_norm", "model.llm.layers.26.attn_sconv", "model.llm.layers.26.mlp.gate", "model.llm.layers.26.mlp.shared_experts", "model.llm.layers.26.mlp_norm", "model.llm.layers.26.mlp_sconv", "model.llm.layers.27.attn", "model.llm.layers.27.attn_norm", "model.llm.layers.27.attn_sconv", "model.llm.layers.27.mlp.gate", "model.llm.layers.27.mlp.shared_experts", "model.llm.layers.27.mlp_norm", "model.llm.layers.27.mlp_sconv", "model.llm.layers.28.attn", "model.llm.layers.28.attn_norm", "model.llm.layers.28.attn_sconv", "model.llm.layers.28.mlp.gate", "model.llm.layers.28.mlp.shared_experts", "model.llm.layers.28.mlp_norm", "model.llm.layers.28.mlp_sconv", "model.llm.layers.29.attn", "model.llm.layers.29.attn_norm", "model.llm.layers.29.attn_sconv", "model.llm.layers.29.mlp.gate", "model.llm.layers.29.mlp.shared_experts", "model.llm.layers.29.mlp_norm", "model.llm.layers.29.mlp_sconv", "model.llm.layers.3.attn", "model.llm.layers.3.attn_norm", "model.llm.layers.3.attn_sconv", "model.llm.layers.3.mlp.gate", "model.llm.layers.3.mlp.shared_experts", "model.llm.layers.3.mlp_norm", "model.llm.layers.3.mlp_sconv", "model.llm.layers.30.attn", "model.llm.layers.30.attn_norm", "model.llm.layers.30.attn_sconv", "model.llm.layers.30.mlp.gate", "model.llm.layers.30.mlp.shared_experts", "model.llm.layers.30.mlp_norm", "model.llm.layers.30.mlp_sconv", "model.llm.layers.31.attn", "model.llm.layers.31.attn_norm", "model.llm.layers.31.attn_sconv", "model.llm.layers.31.mlp.gate", "model.llm.layers.31.mlp.shared_experts", "model.llm.layers.31.mlp_norm", "model.llm.layers.31.mlp_sconv", "model.llm.layers.32.attn", "model.llm.layers.32.attn_norm", "model.llm.layers.32.attn_sconv", "model.llm.layers.32.mlp.gate", "model.llm.layers.32.mlp.shared_experts", "model.llm.layers.32.mlp_norm", "model.llm.layers.32.mlp_sconv", "model.llm.layers.33.attn", "model.llm.layers.33.attn_norm", "model.llm.layers.33.attn_sconv", "model.llm.layers.33.mlp.gate", "model.llm.layers.33.mlp.shared_experts", "model.llm.layers.33.mlp_norm", "model.llm.layers.33.mlp_sconv", "model.llm.layers.34.attn", "model.llm.layers.34.attn_norm", "model.llm.layers.34.attn_sconv", "model.llm.layers.34.mlp.gate", "model.llm.layers.34.mlp.shared_experts", "model.llm.layers.34.mlp_norm", "model.llm.layers.34.mlp_sconv", "model.llm.layers.35.attn", "model.llm.layers.35.attn_norm", "model.llm.layers.35.attn_sconv", "model.llm.layers.35.mlp.gate", "model.llm.layers.35.mlp.shared_experts", "model.llm.layers.35.mlp_norm", "model.llm.layers.35.mlp_sconv", "model.llm.layers.36.attn", "model.llm.layers.36.attn_norm", "model.llm.layers.36.attn_sconv", "model.llm.layers.36.mlp.gate", "model.llm.layers.36.mlp.shared_experts", "model.llm.layers.36.mlp_norm", "model.llm.layers.36.mlp_sconv", "model.llm.layers.37.attn", "model.llm.layers.37.attn_norm", "model.llm.layers.37.attn_sconv", "model.llm.layers.37.mlp.gate", "model.llm.layers.37.mlp.shared_experts", "model.llm.layers.37.mlp_norm", "model.llm.layers.37.mlp_sconv", "model.llm.layers.38.attn", "model.llm.layers.38.attn_norm", "model.llm.layers.38.attn_sconv", "model.llm.layers.38.mlp.gate", "model.llm.layers.38.mlp.shared_experts", "model.llm.layers.38.mlp_norm", "model.llm.layers.38.mlp_sconv", "model.llm.layers.39.attn", "model.llm.layers.39.attn_norm", "model.llm.layers.39.attn_sconv", "model.llm.layers.39.mlp.gate", "model.llm.layers.39.mlp.shared_experts", "model.llm.layers.39.mlp_norm", "model.llm.layers.39.mlp_sconv", "model.llm.layers.4.attn", "model.llm.layers.4.attn_norm", "model.llm.layers.4.attn_sconv", "model.llm.layers.4.mlp.gate", "model.llm.layers.4.mlp.shared_experts", "model.llm.layers.4.mlp_norm", "model.llm.layers.4.mlp_sconv", "model.llm.layers.40.attn", "model.llm.layers.40.attn_norm", "model.llm.layers.40.attn_sconv", "model.llm.layers.40.mlp.gate", "model.llm.layers.40.mlp.shared_experts", "model.llm.layers.40.mlp_norm", "model.llm.layers.40.mlp_sconv", "model.llm.layers.41.attn", "model.llm.layers.41.attn_norm", "model.llm.layers.41.attn_sconv", "model.llm.layers.41.mlp.gate", "model.llm.layers.41.mlp.shared_experts", "model.llm.layers.41.mlp_norm", "model.llm.layers.41.mlp_sconv", "model.llm.layers.42.attn", "model.llm.layers.42.attn_norm", "model.llm.layers.42.attn_sconv", "model.llm.layers.42.mlp.gate", "model.llm.layers.42.mlp.shared_experts", "model.llm.layers.42.mlp_norm", "model.llm.layers.42.mlp_sconv", "model.llm.layers.43.attn", "model.llm.layers.43.attn_norm", "model.llm.layers.43.attn_sconv", "model.llm.layers.43.mlp.gate", "model.llm.layers.43.mlp.shared_experts", "model.llm.layers.43.mlp_norm", "model.llm.layers.43.mlp_sconv", "model.llm.layers.44.attn", "model.llm.layers.44.attn_norm", "model.llm.layers.44.attn_sconv", "model.llm.layers.44.mlp.gate", "model.llm.layers.44.mlp.shared_experts", "model.llm.layers.44.mlp_norm", "model.llm.layers.44.mlp_sconv", "model.llm.layers.45.attn", "model.llm.layers.45.attn_norm", "model.llm.layers.45.attn_sconv", "model.llm.layers.45.mlp.gate", "model.llm.layers.45.mlp.shared_experts", "model.llm.layers.45.mlp_norm", "model.llm.layers.45.mlp_sconv", "model.llm.layers.46.attn", "model.llm.layers.46.attn_norm", "model.llm.layers.46.attn_sconv", "model.llm.layers.46.mlp.gate", "model.llm.layers.46.mlp.shared_experts", "model.llm.layers.46.mlp_norm", "model.llm.layers.46.mlp_sconv", "model.llm.layers.47.attn", "model.llm.layers.47.attn_norm", "model.llm.layers.47.attn_sconv", "model.llm.layers.47.mlp.gate", "model.llm.layers.47.mlp.shared_experts", "model.llm.layers.47.mlp_norm", "model.llm.layers.47.mlp_sconv", "model.llm.layers.48.attn", "model.llm.layers.48.attn_norm", "model.llm.layers.48.attn_sconv", "model.llm.layers.48.mlp.gate", "model.llm.layers.48.mlp.shared_experts", "model.llm.layers.48.mlp_norm", "model.llm.layers.48.mlp_sconv", "model.llm.layers.49.attn", "model.llm.layers.49.attn_norm", "model.llm.layers.49.attn_sconv", "model.llm.layers.49.mlp.gate", "model.llm.layers.49.mlp.shared_experts", "model.llm.layers.49.mlp_norm", "model.llm.layers.49.mlp_sconv", "model.llm.layers.5.attn", "model.llm.layers.5.attn_norm", "model.llm.layers.5.attn_sconv", "model.llm.layers.5.mlp.gate", "model.llm.layers.5.mlp.shared_experts", "model.llm.layers.5.mlp_norm", "model.llm.layers.5.mlp_sconv", "model.llm.layers.50.attn", "model.llm.layers.50.attn_norm", "model.llm.layers.50.attn_sconv", "model.llm.layers.50.mlp.gate", "model.llm.layers.50.mlp.shared_experts", "model.llm.layers.50.mlp_norm", "model.llm.layers.50.mlp_sconv", "model.llm.layers.51.attn", "model.llm.layers.51.attn_norm", "model.llm.layers.51.attn_sconv", "model.llm.layers.51.mlp.gate", "model.llm.layers.51.mlp.shared_experts", "model.llm.layers.51.mlp_norm", "model.llm.layers.51.mlp_sconv", "model.llm.layers.52.attn", "model.llm.layers.52.attn_norm", "model.llm.layers.52.attn_sconv", "model.llm.layers.52.mlp.gate", "model.llm.layers.52.mlp.shared_experts", "model.llm.layers.52.mlp_norm", "model.llm.layers.52.mlp_sconv", "model.llm.layers.53.attn", "model.llm.layers.53.attn_norm", "model.llm.layers.53.attn_sconv", "model.llm.layers.53.mlp.gate", "model.llm.layers.53.mlp.shared_experts", "model.llm.layers.53.mlp_norm", "model.llm.layers.53.mlp_sconv", "model.llm.layers.54.attn", "model.llm.layers.54.attn_norm", "model.llm.layers.54.attn_sconv", "model.llm.layers.54.mlp.gate", "model.llm.layers.54.mlp.shared_experts", "model.llm.layers.54.mlp_norm", "model.llm.layers.54.mlp_sconv", "model.llm.layers.55.attn", "model.llm.layers.55.attn_norm", "model.llm.layers.55.attn_sconv", "model.llm.layers.55.mlp.gate", "model.llm.layers.55.mlp.shared_experts", "model.llm.layers.55.mlp_norm", "model.llm.layers.55.mlp_sconv", "model.llm.layers.56.attn", "model.llm.layers.56.attn_norm", "model.llm.layers.56.attn_sconv", "model.llm.layers.56.mlp.gate", "model.llm.layers.56.mlp.shared_experts", "model.llm.layers.56.mlp_norm", "model.llm.layers.56.mlp_sconv", "model.llm.layers.57.attn", "model.llm.layers.57.attn_norm", "model.llm.layers.57.attn_sconv", "model.llm.layers.57.mlp.gate", "model.llm.layers.57.mlp.shared_experts", "model.llm.layers.57.mlp_norm", "model.llm.layers.57.mlp_sconv", "model.llm.layers.58.attn", "model.llm.layers.58.attn_norm", "model.llm.layers.58.attn_sconv", "model.llm.layers.58.mlp.gate", "model.llm.layers.58.mlp.shared_experts", "model.llm.layers.58.mlp_norm", "model.llm.layers.58.mlp_sconv", "model.llm.layers.59.attn", "model.llm.layers.59.attn_norm", "model.llm.layers.59.attn_sconv", "model.llm.layers.59.mlp.gate", "model.llm.layers.59.mlp.shared_experts", "model.llm.layers.59.mlp_norm", "model.llm.layers.59.mlp_sconv", "model.llm.layers.6.attn", "model.llm.layers.6.attn_norm", "model.llm.layers.6.attn_sconv", "model.llm.layers.6.mlp.gate", "model.llm.layers.6.mlp.shared_experts", "model.llm.layers.6.mlp_norm", "model.llm.layers.6.mlp_sconv", "model.llm.layers.60.attn", "model.llm.layers.60.attn_norm", "model.llm.layers.60.attn_sconv", "model.llm.layers.60.mlp.gate", "model.llm.layers.60.mlp.shared_experts", "model.llm.layers.60.mlp_norm", "model.llm.layers.60.mlp_sconv", "model.llm.layers.61.attn", "model.llm.layers.61.attn_norm", "model.llm.layers.61.attn_sconv", "model.llm.layers.61.mlp.gate", "model.llm.layers.61.mlp.shared_experts", "model.llm.layers.61.mlp_norm", "model.llm.layers.61.mlp_sconv", "model.llm.layers.62.attn", "model.llm.layers.62.attn_norm", "model.llm.layers.62.attn_sconv", "model.llm.layers.62.mlp.gate", "model.llm.layers.62.mlp.shared_experts", "model.llm.layers.62.mlp_norm", "model.llm.layers.62.mlp_sconv", "model.llm.layers.63.attn", "model.llm.layers.63.attn_norm", "model.llm.layers.63.attn_sconv", "model.llm.layers.63.mlp.gate", "model.llm.layers.63.mlp.shared_experts", "model.llm.layers.63.mlp_norm", "model.llm.layers.63.mlp_sconv", "model.llm.layers.64.attn", "model.llm.layers.64.attn_norm", "model.llm.layers.64.attn_sconv", "model.llm.layers.64.mlp.gate", "model.llm.layers.64.mlp.shared_experts", "model.llm.layers.64.mlp_norm", "model.llm.layers.64.mlp_sconv", "model.llm.layers.65.attn", "model.llm.layers.65.attn_norm", "model.llm.layers.65.attn_sconv", "model.llm.layers.65.mlp.gate", "model.llm.layers.65.mlp.shared_experts", "model.llm.layers.65.mlp_norm", "model.llm.layers.65.mlp_sconv", "model.llm.layers.7.attn", "model.llm.layers.7.attn_norm", "model.llm.layers.7.attn_sconv", "model.llm.layers.7.mlp.gate", "model.llm.layers.7.mlp.shared_experts", "model.llm.layers.7.mlp_norm", "model.llm.layers.7.mlp_sconv", "model.llm.layers.8.attn", "model.llm.layers.8.attn_norm", "model.llm.layers.8.attn_sconv", "model.llm.layers.8.mlp.gate", "model.llm.layers.8.mlp.shared_experts", "model.llm.layers.8.mlp_norm", "model.llm.layers.8.mlp_sconv", "model.llm.layers.9.attn", "model.llm.layers.9.attn_norm", "model.llm.layers.9.attn_sconv", "model.llm.layers.9.mlp.gate", "model.llm.layers.9.mlp.shared_experts", "model.llm.layers.9.mlp_norm", "model.llm.layers.9.mlp_sconv" ], "modelopt_quant_config": { "quant_cfg": { "*weight_quantizer": { "num_bits": [ 2, 1 ], "block_sizes": { "-1": 16, "type": "dynamic", "scale_bits": [ 4, 3 ] }, "axis": null, "enable": true }, "*input_quantizer": { "num_bits": [ 2, 1 ], "block_sizes": { "-1": 16, "type": "dynamic", "scale_bits": [ 4, 3 ] }, "axis": null, "enable": true }, "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 } }, "algorithm": "max" }, "group_size": 16 } }