Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
PrefixLM Attention on Llama3.1 405B (q=128, k=8) (1k)
Loading...
122.22
PrefixLM Attention TFLOPS (1k)
CuBridge
10.3368
39.3834
68.43
97.4766
May 6, 2026
PrefixLM Attention TFLOPS (1k)
Updated 27d ago
Evaluation Results
Method
Method
Links
PrefixLM Attention TFLOPS (1k)
CuBridge
Implementation=CuBridge
2026.05
122.22
FlexAttention
Implementation=PyTorch...
2026.05
107.89
Qimeng Attn
Implementation=Qimeng...
2026.05
76.01
Torch
Implementation=Standar...
2026.05
14.64
Feedback
Search any
task
Search any
task