Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Query Attention (MQA) Performance on NVIDIA A100 GPU
Loading...
211.4
TFLOPS
cuDNN
154.304
169.127
183.95
198.773
Jun 14, 2025
TFLOPS
Speedup
Updated 1mo ago
Evaluation Results
Method
Method
Links
TFLOPS
Speedup
cuDNN
Head Dimension=128, Se...
2025.06
211.4
-
DeepSeek-V3 + Ours
Head Dimension=64, Seq...
2025.06
156.5
5.36
Feedback
Search any
task
Search any
task
