Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Head Attention (MHA) Performance on NVIDIA RTX8000 GPU
Loading...
49.9
TFLOPS
DeepSeek-V3 + Ours
16.828
25.414
34
42.586
Jun 14, 2025
TFLOPS
Speedup
Updated 4d ago
Evaluation Results
Method
Method
Links
TFLOPS
Speedup
DeepSeek-V3 + Ours
Head Dimension=64, Seq...
2025.06
49.9
-
flash-attn v1
Head Dimension=64, Seq...
2025.06
18.1
-
Feedback
Search any
task
Search any
task
