[Perf][1/N] w8a8c8 support in dsv3.2/glm5 (#7029)

### What this PR does / why we need it?
This PR supports W8A8C8 in dsv3.2/glm5 with lightning_indexer_quant ops
in pd-mix stage mainly.

Because the code for the current PD-disaggregated scenario is still
under refactoring and cleanup, this PR prioritizes ensuring the C8
functionality in the pd-mix scenario.

The next steps are planned in two parts:
① Once the optimized scatter operator is updated, we will replace the
original operator to improve the performance of storing k_scale.
② Once the code logic for the PD-disaggregated scenario becomes stable,
we will carry out more comprehensive validation and make appropriate
adaptations.
③ Because enabling C8 currently introduces several new operators whose
performance still needs improvement, performance may regress in some
scenarios. Therefore, only after all the operators are fully ready can
we ensure that this feature does not cause any performance degradation.
At that point, we will enable this feature by default and remove the
switch in `additional_config`.


### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

---------

Signed-off-by: rjg-lyh <1318825571@qq.com>

vllm_ascend/ascend_config.py

@@ -134,9 +134,12 @@ class AscendConfig:
             bool(additional_config.get("enable_async_exponential", False)) and not vllm_is_batch_invariant()
         )
 
+        use_sparse = hasattr(vllm_config.model_config, "hf_text_config") and hasattr(
+            vllm_config.model_config.hf_text_config, "index_topk"
+        )
+
         self.enable_kv_nz = additional_config.get("enable_kv_nz", False)
         if self.enable_kv_nz:
-            use_sparse = hasattr(vllm_config.model_config.hf_text_config, "index_topk")
             if not vllm_config.model_config.is_deepseek_mla or use_sparse:
                 raise RuntimeError("enable_kv_nz is only supported for mla currently.")
             if vllm_config.kv_transfer_config is None or not vllm_config.kv_transfer_config.is_kv_consumer:
@@ -144,6 +147,17 @@ class AscendConfig:
                     "enable_kv_nz is only supported in pd scenario and can only be used in D node."
                 )
 
+        from vllm_ascend.utils import AscendDeviceType, get_ascend_device_type
+
+        # Disable Sparse C8 for A5
+        # A5 has not been fully validated for this path and may carry hidden risks.
+        # TODO(rjg-lyh): Enable A5 support after sufficient validation.
+        self.enable_sparse_c8 = (
+            additional_config.get("enable_sparse_c8", False)
+            and use_sparse
+            and get_ascend_device_type() != AscendDeviceType.A5
+        )
+
     def _construct_weight_prefetch_config(self, additional_config):
         weight_prefetch_config = additional_config.get("weight_prefetch_config", {})
         self.weight_prefetch_config = WeightPrefetchConfig(weight_prefetch_config)