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

Fix cache type in Idefics2 #30729

Merged
merged 2 commits into from
May 14, 2024
Merged

Fix cache type in Idefics2 #30729

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6985a27
standardize cache in idefics2
zucchini-nlp May 9, 2024
1459750
Merge remote-tracking branch 'upstream/main' into idefix_cache
zucchini-nlp May 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
10 changes: 7 additions & 3 deletions src/transformers/models/idefics2/modeling_idefics2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1591,9 +1591,10 @@ def forward(
raise ValueError("You have to specify either input_ids or inputs_embeds")

past_seen_tokens = 0
if use_cache:
if not isinstance(past_key_values, Cache):
past_key_values = DynamicCache.from_legacy_cache(past_key_values)
return_legacy_cache = False
if use_cache and not isinstance(past_key_values, Cache): # kept for BC (non `Cache` `past_key_values` inputs)
return_legacy_cache = True
past_key_values = DynamicCache.from_legacy_cache(past_key_values)
past_seen_tokens = past_key_values.get_usable_length(seq_length)

if inputs_embeds is not None and input_ids is None and past_seen_tokens == 0:
Expand Down Expand Up @@ -1667,6 +1668,9 @@ def forward(
return_dict=return_dict,
)

if return_legacy_cache:
outputs.past_key_values = outputs.past_key_values.to_legacy_cache()

if not return_dict:
return tuple(v for v in [*outputs, image_hidden_states] if v is not None)

Expand Down