Skip to content

Update README.md #573

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
byshiue merged 1 commit into from
Jun 23, 2020
Merged

Update README.md #573

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions FasterTransformer/v2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -564,7 +564,7 @@ python encoder_sample.py \
`./bin/decoding_gemm` can generate the best GEMM configuration. The arguments of `decoding_gemm` are:

```bash
./bin/decoding_gemm <batch_size> <beam_width> <head_number> <size_per_head> <sequence_length> <encoder_hidden_dim> <is_use_fp16>
./bin/decoding_gemm <batch_size> <beam_width> <head_number> <size_per_head> <vocab_size> <sequence_length> <encoder_hidden_dim> <is_use_fp16>
```

Assume the settings of decoding are as follows.
Expand Down Expand Up @@ -593,7 +593,7 @@ a. Run the decoding in C++ by running the following script:
`./bin/decoding_sample` runs the decoding in the `cpp`. The arguments of `encoder_sample` is:

```bash
./bin/decoding_sample <batch_size> <beam_width> <head_number> <size_per_head> <sequence_length> <num_layers> <encoder_hidden_dim> <is_use_fp16>
./bin/decoding_sample <batch_size> <beam_width> <head_number> <size_per_head> <vocab_size> <sequence_length> <num_layers> <encoder_hidden_dim> <is_use_fp16>
```

Then the following scripts can run the decoding under the above settings.
Expand Down