diff --git a/examples/llama-4/scout-qlora-flexattn-fsdp2.yaml b/examples/llama-4/scout-qlora-flexattn-fsdp2.yaml index b319349c4..b3e8c328c 100644 --- a/examples/llama-4/scout-qlora-flexattn-fsdp2.yaml +++ b/examples/llama-4/scout-qlora-flexattn-fsdp2.yaml @@ -74,7 +74,7 @@ fsdp: fsdp_config: fsdp_version: 2 fsdp_offload_params: false - fsdp_cpu_ram_efficient_loading: true + # fsdp_cpu_ram_efficient_loading: true # does not work with load_in_8bit/4bit fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP fsdp_transformer_layer_cls_to_wrap: Llama4TextDecoderLayer fsdp_state_dict_type: SHARDED_STATE_DICT