minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Fix benchmark import for should_use_tensor_core (#17232)

Browse Source
This commit is contained in:
Mohammad Miadh Angkad
2026-01-16 17:48:36 -05:00
committed by GitHub
parent 4229de3b13
commit b0701f02b3
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/kernels/decoding_attention_triton/triton_flashinfer_cudnn.py
+1 -1
View File
@@ -6,8 +6,8 @@ import torch
import torch.utils.benchmark as benchmark import torch.utils.benchmark as benchmark
from flashinfer import BatchDecodeWithPagedKVCacheWrapper 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.layers.attention.triton_ops.decode_attention import decode_attention_fwd
from sglang.srt.utils import should_use_tensor_core
def benchmark_forward( def benchmark_forward(