Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling Inference on Qwen2.5-7B (4K Context Length)
Loading...
6.2
Decode Latency (ms/token)
FastMKA
5.88
8.04
10.2
12.36
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
6.2
1.4
MLA
Batch size=1, Precisio...
2026.03
8.7
-
GQA
Batch size=1, Precisio...
2026.03
12.4
-
MHA
Batch size=1, Precisio...
2026.03
14.2
-
Feedback
Search any
task
Search any
task