Skip to content
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

Jump to bottom

[Doc] Fix typo in gpt_guide.md #682

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[Doc] Fix typo in gpt_guide.md #682

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
2 changes: 1 addition & 1 deletion docs/gpt_guide.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,7 @@ In summary, the workflow to run the GPT model is:

1. Initializing the NCCL comm and setting ranks of tensor parallel and pipeline parallel by MPI or threading
2. Load weights by the ranks of tensor parallel, pipeline parallel and other model hyper-parameters.
3. Create the instance of `ParalelGpt` by the ranks of tensor parallel, pipeline parallel and other model hyper-parameters.
3. Create the instance of `ParallelGpt` by the ranks of tensor parallel, pipeline parallel and other model hyper-parameters.
4. Receive the request from client and convert the request to the format of input tensors for ParallelGpt.
5. Run forward
6. Convert the output tensors of ParallelGpt to response of client and return the response.
Expand Down