Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual-Language Model Inference on VILA A100
Loading...
155.3
Throughput (tokens/sec)
VILA-7B-AWQ
44.228
73.064
101.9
130.736
Jun 1, 2023
Throughput (tokens/sec)
Updated 2mo ago
Evaluation Results
Method
Method
Links
Throughput (tokens/sec)
VILA-7B-AWQ
Precision=W4A16
2023.06
155.3
VILA-13B-AWQ
Precision=W4A16
2023.06
102.1
VILA-7B
Precision=FP16
2023.06
81.6
VILA-13B
Precision=FP16
2023.06
48.5
Feedback
Search any
task
Search any
task