List your company

GPU Inference Throughput on A100-SXM4-40GB

5,081Throughput (tok/s)DF-SSM
-188.681,179.412,547.53,915.59Apr 28, 2026

Evaluation results

MethodLinks
DF-SSMBatch=5122026.045,081—
DF-SSMBatch=1282026.043,996—
DF-SSMBatch=322026.041,9634.1
DF-SSMBatch=82026.046475.6
FP16 mamba-ssmBatch=322026.04482—
DF-SSMBatch=12026.0429921.4
FP16 mamba-ssmBatch=82026.04116—
FP16 mamba-ssmBatch=12026.0414—