[Model] GLM5 adaptation (#6642)

### What this PR does / why we need it?
GLM5 adaptation
1. use torch_npu.npu_lightning_indexer for GLM5
2. forbid eagle proposer when fullgraph mode is enabled because of bugs
3. add quatization config for GLM5
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
by ci
- vLLM main:
978a37c823

---------

Signed-off-by: yydyzr <liuyuncong1@huawei.com>
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
Co-authored-by: shenchuxiaofugui <1311027364@qq.com>

vllm_ascend/quantization/modelslim_config.py

@@ -96,6 +96,11 @@ packed_modules_model_mapping: dict[str, dict[str, list[str]]] = {
         "experts": ["experts.0.gate_proj", "experts.0.up_proj", "experts.0.down_proj"],
         "fused_qkv_a_proj": ["q_a_proj", "kv_a_proj_with_mqa"],
     },
+    "glm_moe_dsa": {
+        "gate_up_proj": ["gate_proj", "up_proj"],
+        "experts": ["experts.0.gate_proj", "experts.0.up_proj", "experts.0.down_proj"],
+        "fused_qkv_a_proj": ["q_a_proj", "kv_a_proj_with_mqa"],
+    },
     # NOTE 1.The quantized MTP layer of deepseek on the NPU is not quantized;
     # NOTE 2.The description file generated by the current msmodelslim tool does not have
     # MTP layer info. Please manually add it and set the value to FLOAT.