Fix NVFP4 config-building crash (dict-vs-list format assumption) in build_quant_cfg

serve_cosmos3_i2v4step_diffusers.py

@@ -100,15 +100,18 @@ def build_quant_cfg(fmt: str) -> dict:
         }
     if fmt == "nvfp4":
         import copy
+        # Return the base preset UNMODIFIED -- on this installed modelopt version,
+        # W4A16_NVFP4_CFG's quant_cfg is a LIST (newer format), not the dict this
+        # function used to assume (confirmed empirically: "TypeError: list indices
+        # must be integers or slices, not str" trying dict-style key assignment
+        # here). enforce_weight_only_and_spare() below disables activations/spares
+        # on the model's actual inserted quantizer modules AFTER mtq.quantize(),
+        # which is config-form agnostic -- no need to pre-bake into the config dict.
+        # load_cosmos3_modelopt.py's loader re-applies the same disabling on every
+        # restore anyway (modelopt_state replays the config, not our imperative
+        # .disable() calls), so skipping the pre-bake here loses nothing.
         base = getattr(mtq, "W4A16_NVFP4_CFG", None) or mtq.NVFP4_DEFAULT_CFG
-        cfg = copy.deepcopy(base)
-        cfg.setdefault("quant_cfg", {})
-        cfg["quant_cfg"]["*input_quantizer"] = {"enable": False}
-        cfg["quant_cfg"]["*output_quantizer"] = {"enable": False}
-        cfg["quant_cfg"]["*softmax_quantizer"] = {"enable": False}
-        for s in SPARE_SUBSTRINGS:
-            cfg["quant_cfg"][f"*{s}*weight_quantizer"] = {"enable": False}
-        return cfg
+        return copy.deepcopy(base)
     raise ValueError(f"Unknown format: {fmt!r}")