From f3ba87046320b94f23ec9ce765b214625f87cd9b Mon Sep 17 00:00:00 2001 From: Jou-An Chen Date: Wed, 24 Sep 2025 18:02:10 -0700 Subject: [PATCH] Fix llama model o_proj lora_ids passing for finite lorax Signed-off-by: Jou-An Chen --- QEfficient/transformers/models/llama/modeling_llama.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/QEfficient/transformers/models/llama/modeling_llama.py b/QEfficient/transformers/models/llama/modeling_llama.py index a285f00dc..5106e2dc4 100644 --- a/QEfficient/transformers/models/llama/modeling_llama.py +++ b/QEfficient/transformers/models/llama/modeling_llama.py @@ -174,7 +174,7 @@ def forward( ) attn_output = attn_output.reshape(*input_shape, -1).contiguous() - attn_output = self.o_proj(attn_output) + attn_output = self.o_proj(attn_output, **kwargs) return attn_output, attn_weights, past_key_value