[Intel HPU] change MoE weights and scales from list to tensor and add… (#5289)

* [Intel HPU] change MoE weights and scales from list to tensor and add q/k rms norm

* update doc

* move HPU_CHUNK_SIZE into envs

fastdeploy/envs.py

@@ -148,6 +148,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
     "FD_ENGINE_TASK_QUEUE_WITH_SHM": lambda: int(os.getenv("FD_ENGINE_TASK_QUEUE_WITH_SHM", "0")),
     "FD_FILL_BITMASK_BATCH": lambda: int(os.getenv("FD_FILL_BITMASK_BATCH", "4")),
     "FD_ENABLE_PDL": lambda: int(os.getenv("FD_ENABLE_PDL", "1")),
+    # "Number of tokens in the group for Mixture of Experts (MoE) computation processing on HPU"
+    "FD_HPU_CHUNK_SIZE": lambda: int(os.getenv("FD_HPU_CHUNK_SIZE", "64")),
 }