Skip to content

[Model] Ignore rotary embed load for Cohere model #17319

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
Apr 29, 2025
Merged

[Model] Ignore rotary embed load for Cohere model #17319

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: 4 additions & 0 deletions vllm/model_executor/models/commandr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -418,6 +418,10 @@ def load_weights(self, weights: Iterable[Tuple[str,
loaded_params: Set[str] = set()
for name, loaded_weight in weights:

# Skip loading rotary embeddings since vLLM has its own
if "rotary_emb.inv_freq" in name:
continue

if (self.quant_config is not None and
(scale_name := self.quant_config.get_cache_scale(name))):
# Loading kv cache quantization scales
Expand Down