[Spec Decode]clean up spec decode interface (#6947)

This pull request refactors the speculative decoding proposer interface
to align with upstream vLLM, removing the local `Proposer` interface and
renaming methods to `propose`.

This is the first step. In the future we should remove the class
register and just add few Ascend specified method once the arch in vLLM
is ready.

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

vllm_ascend/spec_decode/eagle_proposer.py

@@ -30,8 +30,7 @@ from vllm.utils.platform_utils import is_pin_memory_available
 from vllm.v1.attention.backends.utils import CommonAttentionMetadata
 from vllm.v1.core.sched.output import SchedulerOutput
 from vllm.v1.sample.metadata import SamplingMetadata
-from vllm.v1.spec_decode.eagle import PADDING_SLOT_ID
-from vllm.v1.spec_decode.eagle import EagleProposer as VllmEagleProposer
+from vllm.v1.spec_decode.eagle import PADDING_SLOT_ID, EagleProposer
 from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
 from vllm.v1.worker.gpu_input_batch import CachedRequestState, InputBatch
 
@@ -81,7 +80,7 @@ def split_inputs_tp_to_sp(hidden_states, out):
     return out[:padded_num_tokens_per_rank]
 
 
-class EagleProposer(VllmEagleProposer):
+class AscendEagleProposer(EagleProposer):
     _runnable: ACLGraphWrapper | Callable
 
     def __init__(self, vllm_config: VllmConfig, device: torch.device, runner=None):