[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/torch_binding.cpp

@@ -739,7 +739,7 @@ at::Tensor npu_lightning_indexer(
     char *query_layout_ptr = const_cast<char *>(query_layout_str.c_str());
     char *key_layout_ptr = const_cast<char *>(key_layout_str.c_str());
     EXEC_NPU_CMD(
-        aclnnLightningIndexer,
+        aclnnLightningIndexerVllm,
         query,
         key,
         weights,