[CI/UT][bugfix] fix v0 spec decode (#1321)

### What this PR does / why we need it?
1. [PR913](https://github.com/vllm-project/vllm-ascend/pull/913)
introduced an error that caused V0's spec decode function to fail.
[PR1109](https://github.com/vllm-project/vllm-ascend/pull/1109) wanted
to fix this problem. Unfortunately, the fix broke the ngram function. I
fixed the ngram function in this PR. **PS**: Q: Why is there a problem
when ngram is not found when pr1109 is merged? A: The newly introduced
problem will only appear when tp>1, and the use cases on CI are all tp=1
2. In versions after 0.7.3, vllm-ascend deleted some spec decode UTs to
avoid CI taking too long, including eagle speculative UTs, which made CI
unable to take care of the eagle function. I added
it(`test_eagle_correctness.py`) back in this PR
3. Because of the reason mentioned in 2, the current version of Eagle
has a problem. I located and fixed this problem. It was because vllm's
`draft_model_runner.py` was changed and vllm-ascend was not synchronized
in time.
4. Currently, the UTs of v0 and v1 are mixed in the spec_decode
directory. I split them into two directories: spec_decode_v0 and
spec_decode_v1.
5. i found
`vllm.spec_decode.multi_step_worker.MultiStepWorker.set_include_gpu_probs_tensor`
and
`vllm.spec_decode.multi_step_worker.MultiStepWorker.set_should_modify_greedy_probs_inplace`
have changed in vllm, so i remove it in this pr.

### Does this PR introduce _any_ user-facing change?
This PR fixes the functions of ngram and eagle spec decode in the v0
engine

### How was this patch tested?
tested by CI

Signed-off-by: mengwei805 <mengwei25@huawei.com>

vllm_ascend/worker/draft_model_runner.py

@@ -51,12 +51,6 @@ class TP1DraftModelRunner(ModelRunnerWrapperBase):
     """
 
     def __init__(self, model_runner: ModelRunnerBase):
-        if hasattr(
-                model_runner,
-                "return_hidden_states") and model_runner.return_hidden_states:
-            raise ValueError(
-                "return_hidden_states is not supported for TP1DraftModelRunner."
-            )
         super().__init__(model_runner)
 
         self.indices_of_seq_with_bonus_tokens = None
@@ -211,6 +205,9 @@ class TP1DraftModelRunner(ModelRunnerWrapperBase):
             if self.prompt_adapter_config is not None:
                 raise ValueError("TP1DraftModelRunner has no support for "
                                  "prompt_adapter_config")
+            if model_input.inputs_embeds is not None:
+                raise ValueError("TP1DraftModelRunner has no support for "
+                                 "inputs_embeds")
             if model_input.multi_modal_kwargs:
                 raise ValueError(
                     "TP1DraftModelRunner has no support for multi_modal_kwargs"
@@ -272,6 +269,7 @@ class TP1DraftModelRunner(ModelRunnerWrapperBase):
 
                 hidden_states = model_executable(
                     input_ids=model_input.input_tokens,
+                    inputs_embeds=None,
                     positions=model_input.input_positions,
                     intermediate_tensors=intermediate_tensors,
                     **MultiModalKwargs.as_kwargs(multi_modal_kwargs,
@@ -293,6 +291,9 @@ class TP1DraftModelRunner(ModelRunnerWrapperBase):
             )
             outputs.append(output)
 
+            if self.return_hidden_states and is_fallback:
+                output.hidden_states = hidden_states
+
             if model_input.attn_metadata.num_prefills == 0 \
                 and self.indices_of_seq_with_bonus_tokens is not None:
                 assert output.sampled_token_ids is not None