[MTP] follow custom deepseek modeling changes to support graph mode

[mengwei805]

What this PR does / why we need it?

As custom deepseek modeling do some changes to support graph mode in #585, so i follow it to change custom deepseek_mtp modeling.

And some modifications for k>1 were not carried over by the #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.

#648 did not completely fix the sample change(#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.

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）

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 [V1] Support DeepSeek MTP in V1 vllm#13500.
3. if u run MTP failed by segmentation fault, u can follow v0.7.3 patch v0.7.3 Add MTP support for deepseek #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