support pangu moe

Signed-off-by: angazenn <zengyanjia@huawei.com>

Author: angazenn

vllm_ascend/models/__init__.py

@@ -47,3 +47,7 @@ def register_model():
     ModelRegistry.register_model(
         "Qwen3MoeForCausalLM",
         "vllm_ascend.models.qwen3_moe:CustomQwen3MoeForCausalLM")
+    
+    ModelRegistry.register_model(
+        "PanGuMoEForCausalLM",
+        "vllm_ascend.models.pangu_moe:PanGuMoEForCausalLM")

vllm_ascend/models/configuration_pangu_moe.py

@@ -0,0 +1,87 @@
+# coding=utf-8
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+""" PanGuMoE model configuration"""
+
+from transformers.utils import logging
+from transformers.configuration_utils import PretrainedConfig
+
+
+logger = logging.get_logger(__name__)
+
+PanGuMoE_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class PanGuMoEConfig(PretrainedConfig):
+   
+    model_type = "PanGuMoE"
+    _auto_class = "AutoConfig"
+
+    def __init__(
+        self,
+        vocab_size=161856,
+        hidden_size=5120,
+        num_hidden_layers=48,
+        num_attention_heads=40,
+        num_key_value_heads=8,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        pad_token_id=0,
+        bos_token_id=1,
+        eos_token_id=2,
+        tie_word_embeddings=False,
+        rope_theta=1000000.0,
+        moe_intermediate_size=1344,
+        shared_expert_intermediate_size=5376,
+        num_experts_per_tok=8,
+        num_experts=64,
+        output_router_logits=False,
+        router_aux_loss_coef=0.001,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+
+        # MoE arguments
+        self.moe_intermediate_size = moe_intermediate_size
+        self.shared_expert_intermediate_size = shared_expert_intermediate_size
+        self.num_experts_per_tok = num_experts_per_tok
+        self.num_experts = num_experts
+        self.output_router_logits = output_router_logits
+        self.router_aux_loss_coef = router_aux_loss_coef
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )