[Feature] Integrate Suffix Spec Decoding (#4045)

### What this PR does / why we need it?
This PR integrate suffix decoding (https://arxiv.org/abs/2411.04975)
from vllm (https://github.com/vllm-project/vllm/pull/25784)

#
Suffix Decoding is a dynamic n-gram matching method that:

1. Uses suffix trees to generate speculative tokens quickly using branch
frequency counts.
2. Can keep a history of prior model responses, which tends to work very
well with repetitive agentic use cases.
3. Can be dynamically updated with newly generated tokens, and FIFO
eviction of older requests.
#
### Does this PR introduce _any_ user-facing change?
This feature should be implemented as opt-in and remain seamless for
users who do not require suffix speculative decoding.

For users who wish to enable it, they must first install
arctic-inference:
`pip install arctic-inference
`

After installation, the suffix speculative decoding feature can be
enabled using the following speculative config:
`--speculative_config '{"method": "suffix", "num_speculative_tokens":
5}'
`

### How was this patch tested?
This PR is currently being tested on vLLM
main:83f478bb19
 with PR https://github.com/vllm-project/vllm/pull/25784

In our previous testing, suffix decoding achieved a 13%-30% throughput
improvement over n-gram on the sonnet dataset, tested on vllm-ascend
v0.9.1 with concurrency ranging from 2 to 40.

- vLLM version: v0.11.2

---------

Signed-off-by: fluctlux <38945811+fluctlux@users.noreply.github.com>

vllm_ascend/worker/model_runner_v1.py

@@ -96,6 +96,7 @@ from vllm.v1.pool.metadata import PoolingMetadata
 from vllm.v1.sample.metadata import SamplingMetadata
 from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
 from vllm.v1.spec_decode.ngram_proposer import NgramProposer
+from vllm.v1.spec_decode.suffix_decoding import SuffixDecodingProposer
 from vllm.v1.utils import CpuGpuBuffer
 from vllm.v1.worker.kv_connector_model_runner_mixin import KVConnectorOutput
 from vllm.v1.worker.lora_model_runner_mixin import LoRAModelRunnerMixin
@@ -630,7 +631,8 @@ class NPUModelRunner(LoRAModelRunnerMixin):
         # Set up speculative decoding.
         self.spec_attn_mask = None
         self.drafter: Optional[Union[NgramProposer, EagleProposer, MtpProposer,
-                                     TorchairMtpProposer]] = None
+                                     TorchairMtpProposer,
+                                     SuffixDecodingProposer]] = None
         self.actual_seq_lengths_q: list[int] = []
         self.decode_token_per_req = 1
         if self.speculative_config: