Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Inference Performance Evaluation on 1,424 simulated conversations on AWS EC2 P5 (test)
Loading...
0.92
Latency (s)
π_θ^EAGLE+FP8
0.8
1.61
2.42
3.23
Jun 16, 2026
Latency (s)
MGL Score
QPS
Speedup
Updated 1mo ago
Evaluation Results
Method
Method
Links
Latency (s)
MGL Score
QPS
Speedup
π_θ^EAGLE+FP8
Decoding=Greedy, Preci...
2026.06
0.92
3.8
6.54
4.48
Baseline (π_θ^FP8)
Decoding=N/A, Precisio...
2026.06
1.6
-
3.66
2.5
Baseline (π_θ^BF16)
Decoding=N/A, Precisio...
2026.06
1.69
-
3.4
2.33
Llama 3 70B (π_T)
Decoding=N/A, Precisio...
2026.06
3.92
-
1.46
1
Feedback
Search any
task
Search any
task