diff --git a/vllm/v1/attention/backends/rocm_aiter_fa.py b/vllm/v1/attention/backends/rocm_aiter_fa.py index 14c473a70a..a6826045ef 100644 --- a/vllm/v1/attention/backends/rocm_aiter_fa.py +++ b/vllm/v1/attention/backends/rocm_aiter_fa.py @@ -1181,7 +1181,7 @@ class AiterFlashAttentionImpl(AttentionImpl): ) descale_shape = ( - attn_metadata.query_start_loc[:num_decodes].shape[0] - 1, + num_decodes, key_cache.shape[2], ) unified_attention( @@ -1189,7 +1189,7 @@ class AiterFlashAttentionImpl(AttentionImpl): k=key_cache, v=value_cache, out=output[:num_decode_tokens], - cu_seqlens_q=attn_metadata.query_start_loc[:num_decodes], + cu_seqlens_q=attn_metadata.query_start_loc[: num_decodes + 1], max_seqlen_q=decode_max_query_len, seqused_k=attn_metadata.seq_lens[:num_decodes], max_seqlen_k=attn_metadata.max_seq_len,