Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-Context Generation Efficiency on Qwen2.5-72B
Loading...
4.76
Speedup (8K)
Dustin
3.876
4.1055
4.335
4.5645
Jun 23, 2026
Speedup (8K)
Speedup (16K)
Speedup (32K)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Speedup (8K)
Speedup (16K)
Speedup (32K)
Dustin
Batch Size=16
2026.06
4.76
7.06
9.17
SpecAttn
Batch Size=16
2026.06
3.91
5.62
7.11
Feedback
Search any
task
Search any
task
