[CI/UT][Refactor] move e2e spec decode and deepseek acc test to per pr (#1136)

### What this PR does / why we need it?
1. run deepseek acc ut per pr --- multicard CI time increased by 9 min
2. run spec decode e2e test on v1 per pr --- singlecard CI time
increased by 3 min (partly is disabled due to not work now)
~~3. align the output of whether dbo is enabled or not~~
    The generated results with and without dbo cannot be aligned.

https://github.com/vllm-project/vllm-ascend/actions/runs/15822900528/job/44600029405?pr=1136
4. skip V0 mtp test due to failure in
https://github.com/vllm-project/vllm-ascend/actions/runs/16012172833/job/45171988816
5. fix some version conflicts
### How was this patch tested?
CI passed with new added test.

---------

Signed-off-by: MengqingCao <cmq0113@163.com>

vllm_ascend/worker/npu_input_batch.py

@@ -314,7 +314,7 @@ class InputBatch:
         self.block_table.add_row(request.block_ids, req_index)
 
         if sampling_params := request.sampling_params:
-            if (self.is_spec_decode
+            if ((not vllm_version_is("0.9.1")) and self.is_spec_decode
                     and is_spec_decode_unsupported(sampling_params)):
                 self.spec_decode_unsupported_reqs.add(req_id)
             if sampling_params.sampling_type == SamplingType.GREEDY: