Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Share Question Mask Attention on Llama2-7b (q=32, k=32) (1k)
Loading...
39.81
TFLOPS (Share QK Mask Attention, 1k)
CuBridge
3.9924
13.2912
22.59
31.8888
May 6, 2026
TFLOPS (Share QK Mask Attention, 1k)
Updated 27d ago
Evaluation Results
Method
Method
Links
TFLOPS (Share QK Mask Attention, 1k)
CuBridge
Implementation=CuBridge
2026.05
39.81
FlexAttention
Implementation=PyTorch...
2026.05
29.86
Qimeng Attn
Implementation=Qimeng...
2026.05
12.27
Torch
Implementation=Standar...
2026.05
5.37
Feedback
Search any
task
Search any
task