Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Inference on LLaMA2-7B 1,024 tokens
Loading...
20
Latency (ms)
Thor-U
14.64
50.82
87
123.18
Apr 20, 2026
Latency (ms)
Speedup Factor
Updated 1mo ago
Evaluation Results
Method
Method
Links
Latency (ms)
Speedup Factor
Thor-U
Phase=decode, Quantiza...
2026.04
20
-
M100
Phase=decode, Quantiza...
2026.04
21.34
0.94
M100
Phase=prefill, Quantiz...
2026.04
79
1.95
Thor-U
Phase=prefill, Quantiz...
2026.04
154
-
Feedback
Search any
task
Search any
task
