[Intel HPU] enable tensor_wise_fp8 (#5324)

* [Intel HPU] enable tensor_wise_fp8

* update code based on comments

* fix code style issue

* fix bug about RP 5138

* mv kv_cache modifications to HPU backend

* fix FP8 Precision Issues

* fix FP8 Precision Issues

* Add quantization UT

---------

Co-authored-by: yanfeich <yanfei.cheng@intel.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

fastdeploy/model_executor/models/ernie4_5_moe.py

@@ -762,6 +762,11 @@ class Ernie4_5_MoePretrainedModel(PretrainedModel):
             True,
             tsm.PairFused,
         ),
+        WeightMeta(
+            f".layers.{{{layerid.MOE_LAYER_ID}}}.mlp.experts.{{{layerid.EXPERT_ID}}}.up_gate_proj.weight_scale",
+            True,
+            tsm.PairFused,
+        ),
         WeightMeta(
             f".layers.{{{layerid.MOE_LAYER_ID}}}.mlp.experts.{{{layerid.EXPERT_ID}}}.down_proj.quant_weight",
             False,