Skip to content

[Bugfix] Fix embedding to support 2D inputs #5829

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
merged 1 commit into from
Jun 26, 2024
Merged

[Bugfix] Fix embedding to support 2D inputs #5829

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 vllm/model_executor/layers/vocab_parallel_embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -306,11 +306,11 @@ def forward(self, input_):
self.shard_indices.added_vocab_end_index)
else:
masked_input = input_
# Get the embeddings.
# Get the embeddings.
output_parallel = F.embedding(masked_input.long(), self.weight)
# Mask the output embedding.
if self.tp_size > 1:
output_parallel.masked_fill_(input_mask.unsqueeze(1), 0)
output_parallel.masked_fill_(input_mask.unsqueeze(-1), 0)
# Reduce across all the model parallel GPUs.
output = tensor_model_parallel_all_reduce(output_parallel)
return output
Expand Down