[kernel] add AscendC op: lightning_indexer and sparse_flash_attention (#4625)

### What this PR does / why we need it?
Provide high-performance AscendC operators lightning_indexer and
sparse_flash_attention to boost the execution performance of the
DeepSeek v3.2 model. Meanwhile, adapt the two AscendC operators to
vllm-ascend framework.

### Does this PR introduce _any_ user-facing change?
No (only underlying operator optimizations, with no user-facing changes)

### How was this patch tested?

- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

Signed-off-by: MingYang119 <songmingyang@huawei.com>

csrc/build_aclnn.sh

@@ -11,11 +11,11 @@ if [[ "$SOC_VERSION" =~ ^ascend310 ]]; then
     exit 0
 elif [[ "$SOC_VERSION" =~ ^ascend910b ]]; then
     # ASCEND910B (A2) series
-    CUSTOM_OPS="grouped_matmul_swiglu_quant_weight_nz_tensor_list"
+    CUSTOM_OPS="grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer;sparse_flash_attention"
     SOC_ARG="ascend910b"
 elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
     # ASCEND910C (A3) series
-    CUSTOM_OPS="grouped_matmul_swiglu_quant_weight_nz_tensor_list"
+    CUSTOM_OPS="grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer;sparse_flash_attention"
     SOC_ARG="ascend910_93"
 else
     # others