[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>

vllm_ascend/worker/worker_v1.py

@@ -93,21 +93,6 @@ class NPUWorker(WorkerBase):
         # init ascend config and soc version
         init_ascend_config(vllm_config)
         check_ascend_device_type()
-        use_sparse = False
-        if vllm_config.model_config is not None:
-            use_sparse = hasattr(vllm_config.model_config.hf_config,
-                                 "index_topk")
-        if use_sparse:
-            # Direct import instead of using try_register_lib to ensure proper error handling when
-            # custom_ops is necessary but not available (e.g., in DeepSeek v3.2 deployments)
-            # yapf: disable
-            import custom_ops  # type: ignore # noqa
-
-            # yapf: enable
-            logger.info(
-                "custom_ops module loaded successfully. Custom operators like "
-                "torch.ops.custom.npu_sparse_flash_attention are now available."
-            )
 
         super().__init__(vllm_config=vllm_config,
                          local_rank=local_rank,