Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Model Inference on Sequence Bucket Ultra-long
Loading...
77.97
Latency (ms)
COREY
76.9072
84.0811
91.255
98.4289
Apr 12, 2026
Latency (ms)
Throughput (k tok/s)
DRAM Memory (B/token)
Updated 4d ago
Evaluation Results
Method
Method
Links
Latency (ms)
Throughput (k tok/s)
DRAM Memory (B/token)
COREY
Precision=FP16
2026.04
77.97
840.5
90.6
Static Fusion
Precision=FP16
2026.04
87.22
751.4
102.4
No Fusion
Precision=FP16
2026.04
104.54
626.9
123
Feedback
Search any
task
Search any
task