[MTP] follow custom deepseek modeling changes to support graph mode (#636)

<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

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

As custom deepseek modeling do some changes to support graph mode in
https://github.com/vllm-project/vllm-ascend/pull/585, so i follow it to
change custom deepseek_mtp modeling.

And some modifications for k>1 were not carried over by the
https://github.com/vllm-project/vllm-ascend/pull/429, now i add it.

In order to better take care of the MTP feature in the vllm-ascend
repository, I added cases related to graph mode(torchair), but i skip it
since torchair can not correctly clean up memory in vllmrunner.

Also i add some case for MTP quantization weights, but test weight is
not ready, so i skip it and i will open it when test quant weights is
ready.

https://github.com/vllm-project/vllm-ascend/pull/648 did not completely
fix the sample
change(https://github.com/vllm-project/vllm-ascend/issues/660) issue, I
added the relevant changes.

### Does this PR introduce _any_ user-facing change?
now, u can use following method to use mtp in deepseek v3/r1 float or
quant weights with eager mode.
```python
llm = LLM(
    model="wemaster/deepseek_mtp_main_random_bf16",
    tensor_parallel_size=2,
    speculative_config={
        "num_speculative_tokens": 1,
    },
    enforce_eager=True,
    trust_remote_code=True,
    disable_log_stats=False,
    gpu_memory_utilization=0.8,
    max_model_len=64,
)
```

or use mtp in deepseek v3/r1 float or quant weights with graph
mode（torchair）
```python
llm = LLM(
    model="wemaster/deepseek_mtp_main_random_bf16",
    tensor_parallel_size=2,
    speculative_config={
        "num_speculative_tokens": 1,
    },
    trust_remote_code=True,
    additional_config={
        'enable_graph_mode': True,
    },
    disable_log_stats=False,
    gpu_memory_utilization=0.8,
    max_model_len=64,
)
```

add notes:
1. now, we support k>1, so u can set num_speculative_tokens > 1 if there
is sufficient redundant computing power;
2. MTP is not supported in V1, we will support it when vLLM does it in
https://github.com/vllm-project/vllm/issues/13500.
3. if u run MTP failed by `segmentation fault`, u can follow v0.7.3
patch https://github.com/vllm-project/vllm-ascend/pull/236 file
`vllm_ascend/patch/patch_metrics.py` method
`__npu_async_metrics_collector_init__`

### How was this patch tested?
local tested passed and test by CI

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

vllm_ascend/patch/__init__.py

@@ -114,6 +114,19 @@
 #    Future Plan:
 #       Revert it when the related pr is merged in vllm.
 #
+# ** File: worker/patch_0_8_4/patch_spec_decode_worker.py **
+# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#   1. `vllm.spec_decode.spec_decode_worker.SpecDecodeWorker._configure_model_sampler_for_spec_decode`
+#    Why:
+#       vLLM `Remove Sampler from Model Code` so vllm-ascend needs a patch to run in v0.8.4.
+#    How：
+#       Use vLLM 0.8.4 method tp patch it.
+#    Related PR (if no, explain why): 1. refused by vllm. 2. vllm doesn't support 3. prepare to submit....
+#       - https://github.com/vllm-project/vllm/pull/17084
+#       - https://github.com/vllm-project/vllm-ascend/pull/636
+#    Future Plan:
+#       Follow v0.8.4 version strategy.
+#
 # ** File: worker/patch_common/patch_metrics.py **
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 #   1. `vllm.spec_decode.metrics.AsyncMetricsCollector.maybe_collect_rejsample_metrics`
@@ -158,7 +171,19 @@
 #    Future Plan:
 #       Revert it when the related pr is merged in vllm and vllm-ascend.
 #
-# ** File: worker/patch_common/patch_multi_step_worker.py **
+#   2. `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`
+#    Why:
+#       vLLM `Remove Sampler from Model Code` so vllm-ascend needs adapt to this change.
+#    How：
+#       Use vLLM 0.8.4 method to patch it.
+#    Related PR (if no, explain why): 1. refused by vllm. 2. vllm doesn't support 3. prepare to submit....
+#       - https://github.com/vllm-project/vllm/pull/15195
+#       - https://github.com/vllm-project/vllm-ascend/pull/395
+#    Future Plan:
+#       Remove it when we identify the reasons clearly.
+#
+# ** File: worker/patch_common/patch_spec_decode_worker.py **
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 #   1. `vllm.spec_decode.spec_decode_worker.SpecDecodeWorker.create_worker`
 #    Why: