indexer.weights_proj is uint8 [64,3584] in checkpoint but bf16 [64,7168] in model. The uint8→bf16 unpack logic only ran in the stacked_params loop, so non-stacked NVFP4 params hit a size mismatch assertion.
indexer.weights_proj is uint8 [64,3584] in checkpoint but bf16 [64,7168] in model. The uint8→bf16 unpack logic only ran in the stacked_params loop, so non-stacked NVFP4 params hit a size mismatch assertion.