Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Causal Blockwise Mask Attention on Llama2-7b (q=32, k=32) (1k)
Loading...
35.12
TFLOPS
CuBridge
3.6392
11.8121
19.985
28.1579
May 6, 2026
TFLOPS
Updated 27d ago
Evaluation Results
Method
Method
Links
TFLOPS
CuBridge
Implementation=CuBridge
2026.05
35.12
FlexAttention
Implementation=PyTorch...
2026.05
31.77
Qimeng Attn
Implementation=Qimeng...
2026.05
16.91
Torch
Implementation=Standar...
2026.05
4.85
Feedback
Search any
task
Search any
task