[Ops][Misc] Refactor and optimize CausalConv1d for Ascend (#7495)

### What this PR does / why we need it?
During the prefill phase of Qwen3-Next and Qwen3.5, the
`torch.ops._C_ascend.causal_conv1d_fn` operator exhibits significant
performance bottlenecks. To address this, we have re-implemented the
optimization using `torch.ops._C_ascend.npu_causal_conv1d_custom`.

### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
1 accuracy test
```
[2026-03-20 16:44:22,961] [ais_bench] [INFO] Start launch task state board ...
+-----------------------------+-----------+------------+-------------+----------+-------------------------------------------+---------------------+
| Task Name                   |   Process | Progress   | Time Cost   | Status   | Log Path                                  | Extend Parameters   |
+=============================+===========+============+=============+==========+===========================================+=====================+
| vllm-api-general-chat/gsm8k |   2918978 | NA         | 0:00:01     | finish   | logs/eval/vllm-api-general-chat/gsm8k.out | None                |
+-----------------------------+-----------+------------+-------------+----------+-------------------------------------------+---------------------+
[2026-03-20 16:44:34,284] [ais_bench] [INFO] Evaluation tasks completed.
[2026-03-20 16:44:34,287] [ais_bench] [INFO] Summarizing evaluation results...
dataset    version    metric    mode      vllm-api-general-chat
---------  ---------  --------  ------  -----------------------
gsm8k      271d0b     accuracy  gen                       96.21
```
2 ut modify test
`pytest -sv
/home/c30006096/vllm-ascend/tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_causal_conv1d.py::test_ascend_causal_conv1d`

- vLLM version: v0.17.0
- vLLM main:
8b6325758c

Signed-off-by: wenba0 <3054239545@qq.com>
Signed-off-by: jiaojiao <56385650+wenba0@users.noreply.github.com>

tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_causal_conv1d.py

@@ -157,6 +157,11 @@ def causal_conv1d_fn_pytorch(
     out_ref_tensor = torch.cat(out_ref, dim=0)
     return out_ref_tensor
 
+def to_int64_tuple(t):
+    t = t.to(torch.int64)
+    if t.dim() == 0:
+        return (t.item(),)
+    return tuple(t.tolist())
 
 @pytest.mark.parametrize('has_initial_state', [False, True])
 @pytest.mark.parametrize('itype', [torch.bfloat16])
@@ -227,16 +232,19 @@ def test_ascend_causal_conv1d(dim, width, extra_state_len, seq_len, has_bias,
     x_origin=x.transpose(-1, -2)
     weight_origin=weight.transpose(-1, -2)
     conv_states_origin=conv_states.transpose(-1, -2)
-    out = torch.ops._C_ascend.causal_conv1d_fn(
+    activation_num = 1 if activation else 0
+    out = torch.ops._C_ascend.npu_causal_conv1d_custom(
                     x_origin,
                     weight_origin,
-                    bias,
-                    activation=activation,
                     conv_state=conv_states_origin,
-                    has_initial_state=has_initial_state_tensor,
-                    non_spec_state_indices_tensor=cache_indices,
-                    non_spec_query_start_loc=query_start_loc,
+                    bias_opt=bias,
+                    query_start_loc_opt=to_int64_tuple(query_start_loc),
+                    cache_indices_opt=to_int64_tuple(cache_indices),
+                    initial_state_mode_opt=to_int64_tuple(has_initial_state_tensor),
+                    num_accepted_tokens_opt=[],
+                    activation_mode=activation_num,
                     pad_slot_id=PAD_SLOT_ID,
+                    run_mode=0
                 ).transpose(-1, -2)
     validate_cmp(out, out_ref, itype)
     validate_cmp(conv_states, conv_states_ref, itype)