valid suffix decoding args

Author: fluctlux

vllm_ascend/worker/model_runner_v1.py

@@ -1952,6 +1952,8 @@ def _build_attn_state(self, num_reqs, num_scheduled_tokens,
             if self.drafter and (self.drafter.name == SpecDcodeType.EAGLE
                                  or self.drafter.name == SpecDcodeType.EAGLE3):
                 attn_state = AscendAttentionState.ChunkedPrefill
+            elif self.drafter and self.drafter.name in (SpecDcodeType.NGRAM, SpecDcodeType.SUFFIX):
+                attn_state = AscendAttentionState.DecodeOnly
             else:
                 attn_state = AscendAttentionState.SpecDecoding
         # splitfuse