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

Fix LLaMa beam search when using parallelize #24224

Merged
merged 3 commits into from
Jun 15, 2023
Merged

Fix LLaMa beam search when using parallelize #24224

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7edc640
Fix LLaMa beam search when using parallelize
FeiWang96 Jun 13, 2023
5563a48
fix code format in modeling_llama.py
FeiWang96 Jun 13, 2023
a44abef
fix format of _reorder_cache in modeling_llama.py
FeiWang96 Jun 15, 2023
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
7 changes: 6 additions & 1 deletion src/transformers/models/llama/modeling_llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -760,7 +760,12 @@ def prepare_inputs_for_generation(
def _reorder_cache(past_key_values, beam_idx):
reordered_past = ()
for layer_past in past_key_values:
reordered_past += (tuple(past_state.index_select(0, beam_idx) for past_state in layer_past),)
reordered_past += (
tuple(
past_state.index_select(0, beam_idx.to(past_state.device))
for past_state in layer_past
),
)
return reordered_past


Expand Down