diff --git a/python/sglang/srt/model_executor/cuda_graph_runner.py b/python/sglang/srt/model_executor/cuda_graph_runner.py index 22ed6cc2b..d9a9861cc 100644 --- a/python/sglang/srt/model_executor/cuda_graph_runner.py +++ b/python/sglang/srt/model_executor/cuda_graph_runner.py @@ -307,7 +307,7 @@ class CudaGraphRunner: bs, self.req_pool_indices, self.seq_lens, - forward_batch.seq_lens_sum, + forward_batch.seq_lens_sum + (bs - raw_bs), self.encoder_lens, )