List your company

Inference Latency on GPT-J-6B

0.203Original Inference Time (s)GPT-J-6B (Standard)
-0.0370321.5831843.20344.823616May 14, 2026

Evaluation results

MethodLinks
GPT-J-6B (Standard)Batch Size=4, Seq Length=642026.050.203——
GPT-J-6B (Standard)Batch Size=8, Seq Length=642026.050.4187——
GPT-J-6B (Standard)Batch Size=16, Seq Length=642026.050.7793——
GPT-J-6B (Standard)Batch Size=4, Seq Length=2562026.050.784——
GPT-J-6B (Standard)Batch Size=8, Seq Length=2562026.051.5709——
GPT-J-6B (Standard)Batch Size=16, Seq Length=2562026.052.9893——
GPT-J-6B (Standard)Batch Size=4, Seq Length=10242026.053.0976——
GPT-J-6B (Standard)Batch Size=8, Seq Length=10242026.056.2038——
CBWC+RMSNormBatch Size=4, Seq Length=642026.05—0.19314.89
CBWC+RMSNormBatch Size=4, Seq Length=2562026.05—0.74534.94
CBWC+RMSNormBatch Size=4, Seq Length=10242026.05—2.86377.55
CBWC+RMSNormBatch Size=8, Seq Length=642026.05—0.4014.22
CBWC+RMSNormBatch Size=8, Seq Length=2562026.05—1.46666.64
CBWC+RMSNormBatch Size=8, Seq Length=10242026.05—5.74157.45
CBWC+RMSNormBatch Size=16, Seq Length=642026.05—0.74094.92
CBWC+RMSNormBatch Size=16, Seq Length=2562026.05—2.76017.67