[Hardware][NV] Fix Modelopt model loading for k-v-scales for Llama models. (#11787)

Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Co-authored-by: mgoin <michael@neuralmagic.com>

vllm/model_executor/models/mixtral.py

@@ -452,7 +452,11 @@ class MixtralForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
                 # Skip layers on other devices.
                 if is_pp_missing_parameter(name, self):
                     continue
-
+                if name.endswith("scale"):
+                    # Remapping the name of FP8 kv-scale.
+                    name = maybe_remap_kv_scale_name(name, params_dict)
+                    if name is None:
+                        continue
                 param = params_dict[name]
                 weight_loader = param.weight_loader
                 weight_loader(param, loaded_weight, shard_id)