Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling Inference on Qwen2.5-7B (64K Context Length)
Loading...
13.6
Decode Latency (ms/token)
FastMKA
12.576
19.488
26.4
33.312
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
13.6
1.68
MLA
Batch size=1, Precisio...
2026.03
22.8
-
GQA
Batch size=1, Precisio...
2026.03
33.4
-
MHA
Batch size=1, Precisio...
2026.03
39.2
-
Feedback
Search any
task
Search any
task