[V1][eagle3] Support eagle3 proposer for v1 (#1032)

### What this PR does / why we need it?
This PR implements the Eagle Pososer feature for vLLM v1, which enables
more efficient speculative decoding by using a draft model to predict
potential future tokens.
- The implementation includes the core Eagle algorithm integration with
vLLM's existing architecture, allowing for faster inference while
maintaining output quality.
- This is needed to significantly improve the generation speed of large
language models without compromising on the quality of generated text.

### Does this PR introduce any user-facing change?
Yes, this PR introduces a new speculative decoding mode that can be
enabled via configuration.
- Users can now choose to use Eagle Pososer by setting appropriate flags
in the inference configuration.
- The API remains backward compatible, with the new functionality being
opt-in.

### How was this patch tested?
CI passed with new unit tests added for the Eagle Pososer functionality.
- Benchmark tests were conducted comparing generation speed and quality
with and without Eagle Pososer.
- Integration tests were performed with various model architectures to
ensure compatibility.
- Manual testing was done using different prompt scenarios to verify
output quality remains consistent.
- we test accept rate on one Ascend 910B npu, The acceptance rate
results are basically consistent with those shown here:
https://github.com/vllm-project/vllm/pull/16937
- Currently, we support scenarios where num_spec_tokens <= 2. When
num_spec_tokens > 2, issues such as insufficient GPU memory and operator
computation errors may occur. We will address this in subsequent
updates.
- We will add support for Eagle v1 in future updates.

### Acceptance Test Script
```bash
SCRIPT="/offline/eagle.py"
DATASET="ShareGpt"
MODEL=Meta-Llama-3.1-8B-Instruct
DRAFT=EAGLE3-LLaMA3.1-Instruct-8B

CUDA_VISIBLE_DEVICES="0" VLLM_USE_V1=1 $PYTHON $SCRIPT \
    --dataset $DATASET \
    --num_spec_tokens 2 \
    --max_num_seqs 1 \
    --model_dir $MODEL \
    --eagle_dir $DRAFT \
    --tp 1 \
    --num_prompts 80
```
### Acceptance Test Results
```bash
██████████████████████████████████████████████████████████████████████████████████████████████████████████| 80/80 [21:22<00:00, 16.03s/it, est. speed input: 4.72 toks/s, output: 13.56 toks/s]
-------------------------------------------------------------------------------------
mean acceptance length: 1.63
-------------------------------------------------------------------------------------
total_counts: 8062
acceptance at token 0: 1.00 (8062 times)
acceptance at token 1: 0.70 (5612 times)
acceptance at token 2: 0.47 (3765 times)
```

Closes: https://github.com/vllm-project/vllm-ascend/issues/1004

---------

Signed-off-by: yuancaoyaoHW <a2749322671@gmail.com>

.github/workflows/vllm_ascend_test_long_term.yaml

@@ -100,7 +100,7 @@ jobs:
             # spec decode test
             VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/long_term/spec_decode/e2e/test_v1_mtp_correctness.py
             # TODO: revert me when test_v1_spec_decode.py::test_ngram_correctness is fixed
-            # VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/long_term/spec_decode/e2e/test_v1_spec_decode.py
+            VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/long_term/spec_decode/e2e/test_v1_spec_decode.py
             VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/long_term/spec_decode/e2e/test_mtp_correctness.py  # it needs a clean process
             pytest -sv tests/e2e/long_term/spec_decode --ignore=tests/e2e/long_term/spec_decode/e2e/test_mtp_correctness.py --ignore=tests/e2e/long_term/spec_decode/e2e/test_v1_spec_decode.py --ignore=tests/e2e/long_term/spec_decode/e2e/test_v1_mtp_correctness.py
             pytest -sv tests/e2e/long_term/test_accuracy.py