Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling Inference on Qwen2.5-7B (8K context length)
Loading...
7.1
Decode Latency (ms/token)
FastMKA
6.712
9.331
11.95
14.569
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
7.1
1.44
MLA
Batch size=1, Precisio...
2026.03
10.2
-
GQA
Batch size=1, Precisio...
2026.03
14.8
-
MHA
Batch size=1, Precisio...
2026.03
16.8
-
Feedback
Search any
task
Search any
task