diff --git a/benchmark/kernels/decoding_attention_triton/triton_flashinfer_cudnn.py b/benchmark/kernels/decoding_attention_triton/triton_flashinfer_cudnn.py index b61240b05..94f622bc2 100644 --- a/benchmark/kernels/decoding_attention_triton/triton_flashinfer_cudnn.py +++ b/benchmark/kernels/decoding_attention_triton/triton_flashinfer_cudnn.py @@ -6,8 +6,8 @@ import torch import torch.utils.benchmark as benchmark from flashinfer import BatchDecodeWithPagedKVCacheWrapper +from sglang.srt.layers.attention.flashinfer_backend import should_use_tensor_core from sglang.srt.layers.attention.triton_ops.decode_attention import decode_attention_fwd -from sglang.srt.utils import should_use_tensor_core def benchmark_forward(