Add a unit test for MoE layer. #7069
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lsy323
approved these changes
May 16, 2024
alanwaketan
reviewed
May 19, 2024
| self.w3 = nn.Parameter(torch.empty(config.num_experts, config.intermediate_size, config.dim)) | ||
|
|
||
| def forward(self, x: Tensor, expert_indices: Tensor) -> Tensor: | ||
| w1_weights = self.w1[expert_indices] # [T, A, D, D] |
There was a problem hiding this comment.
The memory consumption here seems pretty high? It's like you have num_token duplicated weights? So this will not introduce extra storage? Or maybe you are just considering inference where T is just 1?
zpcore
pushed a commit
that referenced
this pull request
May 20, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.