diff --git a/vllm/model_executor/models/granitemoe.py b/vllm/model_executor/models/granitemoe.py index 5266951794a80..fd0d4c89a28fe 100644 --- a/vllm/model_executor/models/granitemoe.py +++ b/vllm/model_executor/models/granitemoe.py @@ -324,6 +324,7 @@ class GraniteMoeForCausalLM(nn.Module, SupportsLoRA, SupportsPP): "o_proj", "embed_tokens", "lm_head", + "layer", ] embedding_modules = { "embed_tokens": "input_embeddings",