[Bugfix] eagle and eagle3 spec decode failures and enable e2e test (#2979)

### What this PR does / why we need it?
- Fix the bug https://github.com/vllm-project/vllm-ascend/issues/2978
- Enable e2e test,
- Adapt to scenarios where Speculative tokens are greater than 2,
- Fix the bug that causes Eagle3 inference failures under high
concurrency and improve the acceptance rate of draft models, by
https://github.com/vllm-project/vllm-ascend/pull/2794

### Does this PR introduce _any_ user-facing change?

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

Co-authored-by: hukongyi
[hukongyi@cmbchina.com](mailto:hukongyi@cmbchina.com)
Co-authored-by: guanyuzhu
[zhuguanyu@huawei.com](mailto:zhuguanyu@huawei.com)
Co-authored-by: liumail680
[liumail680@163.com](mailto:liumail680@163.com)


- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9

---------

Signed-off-by: Icey <1790571317@qq.com>

tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 from __future__ import annotations
 
+import os
 import random
 from typing import Any
 
@@ -9,6 +10,8 @@ from vllm import LLM, SamplingParams
 
 from tests.e2e.conftest import VllmRunner
 
+os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
+
 
 @pytest.fixture
 def test_prompts():
@@ -99,7 +102,6 @@ def test_ngram_correctness(
     assert matches > int(0.7 * len(ref_outputs))
 
 
-@pytest.mark.skipif(True, reason="oom in CI, fix me")
 @pytest.mark.parametrize("use_eagle3", [False, True], ids=["eagle", "eagle3"])
 def test_eagle_correctness(
     test_prompts: list[list[dict[str, Any]]],
@@ -111,8 +113,6 @@ def test_eagle_correctness(
     Compare the outputs of a original LLM and a speculative LLM
     should be the same when using eagle speculative decoding.
     '''
-    if not use_eagle3:
-        pytest.skip("Not current support for the test.")
 
     ref_llm = LLM(model=model_name, max_model_len=2048, enforce_eager=True)
     ref_outputs = ref_llm.chat(test_prompts, sampling_config)
@@ -121,7 +121,6 @@ def test_eagle_correctness(
     spec_model_name = eagle3_model_name() if use_eagle3 else eagle_model_name()
     with VllmRunner(
             model_name,
-            trust_remote_code=True,
             enable_chunked_prefill=True,
             max_num_seqs=1,
             max_num_batched_tokens=2048,