Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling Inference on Qwen2.5-7B (16K Context Length)
Loading...
8.4
Decode Latency (ms/token)
FastMKA
7.88
11.39
14.9
18.41
Mar 21, 2026
Decode Latency (ms/token)
Speedup vs MLA
Updated 25d ago
Evaluation Results
Method
Method
Links
Decode Latency (ms/token)
Speedup vs MLA
FastMKA
Batch size=1, Precisio...
2026.03
8.4
1.52
MLA
Batch size=1, Precisio...
2026.03
12.8
-
GQA
Batch size=1, Precisio...
2026.03
18.6
-
MHA
Batch size=1, Precisio...
2026.03
21.4
-
Feedback
Search any
task
Search any
task