fix acc bug

Signed-off-by: LookAround <[email protected]>

Author: LookAround0301

tests/ut/attention/test_mla_v1.py

@@ -484,9 +484,6 @@ def test_compute_prefill_context(self, mock_ring, mock_load):
         chunk_ctx.chunk_seq_lens = [torch.tensor([8])]
         chunk_ctx.chunk_seq_lens_npu = [torch.tensor([8])]
         chunk_ctx.starts = [torch.tensor([0])]
-        chunk_ctx.max_chunk_num = 1
-        chunk_ctx.mask_for_non_zero_chunk = [True]
-        chunk_ctx.local_chunked_kv_lens = [[[[8]]]]
 
         prefill_meta = MagicMock()
         prefill_meta.chunked_context = chunk_ctx

vllm_ascend/attention/attention_v1.py

@@ -37,7 +37,6 @@
 from vllm.v1.kv_cache_interface import AttentionSpec
 
 from vllm_ascend.attention.utils import (AscendCommonAttentionMetadata,
-                                         extract_req_dcp_by_chunk_pcp,
                                          filter_chunked_req_indices,
                                          split_decodes_and_prefills)
 from vllm_ascend.compilation.acl_graph import (get_graph_params,