[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>

csrc/build_aclnn.sh

@@ -24,7 +24,7 @@ elif [[ "$SOC_VERSION" =~ ^ascend910b ]]; then
     ABSOLUTE_CATLASS_PATH=$(cd "${CATLASS_PATH}" && pwd)
     export CPATH=${ABSOLUTE_CATLASS_PATH}:${CPATH}
 
-    CUSTOM_OPS="grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom;moe_gating_top_k;add_rms_norm_bias;apply_top_k_top_p_custom;transpose_kv_cache_by_block;"
+    CUSTOM_OPS="grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer_vllm;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom;moe_gating_top_k;add_rms_norm_bias;apply_top_k_top_p_custom;transpose_kv_cache_by_block;"
     SOC_ARG="ascend910b"
 elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
     # ASCEND910C (A3) series
@@ -68,7 +68,7 @@ elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
 
     CUSTOM_OPS_ARRAY=(
         "grouped_matmul_swiglu_quant_weight_nz_tensor_list"
-        "lightning_indexer"
+        "lightning_indexer_vllm"
         "sparse_flash_attention"
         "dispatch_ffn_combine"
         "dispatch_ffn_combine_bf16"