FasterTransformer icon indicating copy to clipboard operation
FasterTransformer copied to clipboard

Is allow_gemm_test flag effective in the BERT example?

Open dontloo opened this issue 3 years ago • 1 comments

bert_guide.md section 1.1.2 mentioned this allow_gemm_test flag, but it seems this flag is not effective and not used in the bertExample method in bert_example.cc.

Output shows "using default GEMM algo" with allow_gemm_test=1

root@e6efb0f86068:/workspace/FasterTransformer/build# ./bin/bert_example 32 12 32 12 64 0 0 1
[INFO] Device: Tesla T4 
[WARNING] gemm_config.in is not found; using default GEMM algo
[FT][INFO] batch_size 32 seq_len 32 layer 12 FT-CPP-time 42.36 ms (10 iterations) 

dontloo avatar Jul 11 '22 15:07 dontloo

Hi, dontloo. Thank you for the feedback and sorry for the confusion. We have removed this feature but not update the document. We will fix it in the next update.

byshiue avatar Jul 11 '22 23:07 byshiue

bert_guide.md section 1.1.2 mentioned this allow_gemm_test flag, but it seems this flag is not effective and not used in the bertExample method in bert_example.cc.

Output shows "using default GEMM algo" with allow_gemm_test=1

root@e6efb0f86068:/workspace/FasterTransformer/build# ./bin/bert_example 32 12 32 12 64 0 0 1
[INFO] Device: Tesla T4 
[WARNING] gemm_config.in is not found; using default GEMM algo
[FT][INFO] batch_size 32 seq_len 32 layer 12 FT-CPP-time 42.36 ms (10 iterations) 

This bug is fixed in latest release.

byshiue avatar Aug 16 '22 03:08 byshiue

Close this bug because it is inactivated. Feel free to re-open this issue if you still have any problem.

byshiue avatar Sep 08 '22 07:09 byshiue