From b399117e89b323c846186e4c618a764253bc827e Mon Sep 17 00:00:00 2001 From: weiguihua2 Date: Wed, 21 Jan 2026 08:49:05 +0800 Subject: [PATCH] [Bugfix] fix pcp qwen full graph FIA bug (#6037) ### What this PR does / why we need it? In the pcp full graph Qwen model scenario, the inconsistency between the Q shape and actual q len of the FIA operator is fixed. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/2c24bc6996cb165fce92f780b388a5e39b3f4060 Signed-off-by: weiguihua2 --- vllm_ascend/compilation/acl_graph.py | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/vllm_ascend/compilation/acl_graph.py b/vllm_ascend/compilation/acl_graph.py index 28eafed5..ea979fbf 100644 --- a/vllm_ascend/compilation/acl_graph.py +++ b/vllm_ascend/compilation/acl_graph.py @@ -440,11 +440,8 @@ def update_attn_dcp_pcp_params(update_stream, forward_context, runtime_shape): pad_tensor = np.zeros(pad_length, dtype=actual_seq_lengths_kv.dtype) actual_seq_lengths_kv = np.concatenate([actual_seq_lengths_kv, pad_tensor]) - actual_seq_lengths_q = attn_metadata.actual_seq_lengths_q[: attn_metadata.num_decode_tokens] - if runtime_shape - len(actual_seq_lengths_q): - actual_seq_lengths_q = actual_seq_lengths_q + [actual_seq_lengths_q[-1]] * ( - runtime_shape - len(actual_seq_lengths_q) - ) + actual_seq_lengths_q = attn_metadata.actual_seq_lengths_q + if dcp_size > 1: num_heads = num_heads * dcp_size