Attention Operator Throughput on Llama2 7B (32 Q-heads/32 KV-heads/128 Head-dimension)
207.3Attention TFLOPS
flash-attn v2
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.06 | 207.3 | |
2025.06 | 202.7 | |
2025.06 | 201.5 | |
2025.06 | 201.2 | |
2025.06 | 198.3 | |
2025.06 | 197.2 | |
2025.06 | 188.3 | |
2025.06 | 186.7 | |
2025.06 | 180.3 | |
2025.06 | 176.8 | |
2025.06 | 173.4 | |
2025.06 | 167.1 | |
2025.06 | 164.1 | |
2025.06 | 160.6 | |
2025.06 | 158.4 | |
2025.06 | 152.5 | |
2025.06 | 150.2 | |
2025.06 | 142.6 | |
2025.06 | 137.1 | |
2025.06 | 128.6 | |
2025.06 | 122.5 | |
2025.06 | 112.4 | |
2025.06 | 108.6 | |
2025.06 | 82.8 | |
2025.06 | 15.1 | |
2025.06 | 15.1 | |
2025.06 | 14.6 | |
2025.06 | 14.6 | |
2025.06 | 13.3 | |
2025.06 | 10.9 |