polygraphy run \
    ./encoder.onnx \
    --fp16 \
    --onnxrt \
    --trt \
    --atol 1e-3 --rtol 1e-3 \
    --pool-limit workspace:1000000000 \
    --save-engine=./encoder1_fp16.plan  \
    --verbose \
    --onnx-outputs mark all  \
    --trt-outputs mark all \
    --trt-min-shapes  \
                   chunk_xs:[1,67,80] chunk_lens:[1] \
                   offset:[1,1] att_cache:[1,12,4,80,128] \
                   cnn_cache:[1,12,256,7] cache_mask:[1,1,80]  \
    --trt-opt-shapes  \
                   chunk_xs:[16,67,80] chunk_lens:[16] \
                   offset:[16,1] att_cache:[16,12,4,80,128] \
                   cnn_cache:[16,12,256,7] cache_mask:[16,1,80]  \
    --trt-max-shapes  \
                   chunk_xs:[32,67,80] chunk_lens:[32] \
                   offset:[32,1] att_cache:[32,12,4,80,128] \
                   cnn_cache:[32,12,256,7] cache_mask:[32,1,80]  \
    --input-shapes \
                   chunk_xs:[16,67,80] chunk_lens:[16] \
                   offset:[16,1] att_cache:[16,12,4,80,128] \
                   cnn_cache:[16,12,256,7] cache_mask:[16,1,80]  \
    --validate