[Feature] Add docs of batch invariance and make some extra operators patch (#6910)

### What this PR does / why we need it?

This PR add docs of batch invariance and make some extra operators
according to validation result.
please see https://github.com/vllm-project/vllm-ascend/issues/5487 to
track progress.

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

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>

vllm_ascend/sample/sampler.py

@@ -1,4 +1,5 @@
 import torch
+from vllm.model_executor.layers.batch_invariant import vllm_is_batch_invariant
 from vllm.v1.sample.ops.topk_topp_sampler import TopKTopPSampler
 from vllm.v1.sample.sampler import Sampler
 
@@ -73,6 +74,10 @@ class AscendTopKTopPSampler(TopKTopPSampler):
 
     def forward_native(self, logits, generators, k, p):
         """Override pytorch native implementation to torch_npu"""
+        # when batch_invariant mode is enabled, we should use vllm's implementation.
+        # or it will make batch_invariant mode not working.
+        if vllm_is_batch_invariant():
+            return super().forward_native(logits, generators, k, p)
         logits = self.apply_top_k_top_p(logits, k, p)
         logits_to_return = None
         if self.logprobs_mode == "processed_logits":