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

Update summary.md #125

Merged
merged 1 commit into from
Jun 17, 2024
Merged

Update summary.md #125

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: 2 additions & 0 deletions benchmarks/summary.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@ Date | Device | dtype | batch size | cache length |max input length |max output
----| ------- | ------ |---------- | -------------|-----------------|------------------|----------------------
2024-05-14 | TPU v5e-8 | bfloat16 | 512 | 2048 | 1024 | 1024 | 8700
2024-05-14 | TPU v5e-8 | int8 | 1024 | 2048 | 1024 | 1024 | 8746
2024-06-13 | TPU v5e-1 | bfloat16 | 1024 | 2048 | 1024 | 1024 | 4249
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The v5e-1 number looks great! The gap is huge, I'm wondering the v5-8 data parallel didn't compute each token locally.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

+1. Since we are sharding on batch for Gemma 2B, even at naive case (duplicate weights) v5e-8 should have 8 * 4249 = 33k toks/sec

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The prefills are replicated (8 chips computing the same thing) because we are sharding on batch and prefill is of batch=1. There might be other issues. Overall we should recommand v5e-1 for gemma-2b instead.



** NOTE: ** Gemma 2B uses `--shard_on_batch` flag so it's data parallel instead
of model parallel.
Expand Down
Loading