diff --git a/python/sglang/srt/utils/common.py b/python/sglang/srt/utils/common.py index f8d6ec80b1..2c21e384cb 100644 --- a/python/sglang/srt/utils/common.py +++ b/python/sglang/srt/utils/common.py @@ -4052,7 +4052,8 @@ def get_cuda_graph_batch_size_alignment() -> int: alignment *= 2 if require_gathered_buffer(): alignment *= get_parallel().attn_tp_size - if alignment % get_parallel().attn_cp_size != 0: + # TODO: unverified on NVIDIA; drop the gate once validated on CUDA. + if not is_hip() and alignment % get_parallel().attn_cp_size != 0: alignment *= get_parallel().attn_cp_size return alignment