Skip to content

[Bugfix][Model] Make Olmo2Model weight loading return loaded weights #18504

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 2 commits into from
May 22, 2025
Merged

[Bugfix][Model] Make Olmo2Model weight loading return loaded weights #18504

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b56003d
Make Olmo2Model weight loading return loaded weights
2015aroras May 21, 2025
ad22516
Fix formatting using pre-commit
2015aroras May 21, 2025
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
6 changes: 5 additions & 1 deletion vllm/model_executor/models/olmo2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -314,7 +314,8 @@ def forward(
hidden_states = self.norm(hidden_states)
return hidden_states

def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]):
def load_weights(self, weights: Iterable[tuple[str,
torch.Tensor]]) -> set[str]:
stacked_params_mapping = [
# (param_name, shard_name, shard_id)
("qkv_proj", "q_proj", "q"),
Expand All @@ -325,6 +326,7 @@ def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]):
]

params_dict = dict(self.named_parameters(remove_duplicate=False))
loaded_params: set[str] = set()
for name, loaded_weight in weights:
if is_pp_missing_parameter(name, self):
continue
Expand All @@ -347,6 +349,8 @@ def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]):
weight_loader = getattr(param, "weight_loader",
default_weight_loader)
weight_loader(param, loaded_weight)
loaded_params.add(name)
return loaded_params


class Olmo2ForCausalLM(nn.Module, SupportsPP):
Expand Down