Skip to content

Mllama_fix #369

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
quic-amitraj merged 1 commit into from
Apr 18, 2025
Merged

Mllama_fix #369

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
15 changes: 1 addition & 14 deletions QEfficient/transformers/models/mllama/modeling_mllama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,19 +55,8 @@ class QEffMllamaRotaryEmbedding(MllamaRotaryEmbedding):
- Add static sin/cos computations.
"""

def __init__(
self,
dim=None,
max_position_embeddings=2048,
base=10000,
device=None,
scaling_factor=1.0,
rope_type="default",
config: Optional[MllamaConfig] = None,
):
def __init__(self, config: MllamaConfig, device=None):
super().__init__(config=config)
inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device, **self.rope_kwargs)
self.register_buffer("inv_freq", inv_freq, persistent=False)

# Build here to make `torch.jit.trace` work.
self._set_cos_sin_cache(
Expand Down Expand Up @@ -868,7 +857,6 @@ def forward(
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
cache_position: Optional[torch.LongTensor] = None,
num_logits_to_keep: int = 0,
) -> Union[Tuple, CausalLMOutputWithPast]:
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
output_hidden_states = (
Expand Down Expand Up @@ -935,7 +923,6 @@ def forward(
output_attentions=output_attentions,
return_dict=return_dict,
cache_position=cache_position,
num_logits_to_keep=num_logits_to_keep,
)

return outputs
Expand Down
Loading