Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Inference on MNLI (Latency, Throughput, Memory)
Loading...
22.52
Latency (ms)
flashsvd15
21.3672
29.1486
36.93
44.7114
May 8, 2026
Latency (ms)
Throughput
Peak Memory (MB)
Updated 22d ago
Evaluation Results
Method
Method
Links
Latency (ms)
Throughput
Peak Memory (MB)
flashsvd15
Backend=flashsvd15, Pr...
2026.05
22.52
1,421
343.9
sdpa
Backend=sdpa, Precisio...
2026.05
25.33
1,263.1
605.2
flashsvd
Backend=flashsvd, Prec...
2026.05
44.4
720.8
341.4
naive
Backend=naive, Precisi...
2026.05
51.34
623.3
989.2
Feedback
Search any
task
Search any
task