diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py index a9a4497a3e..0b85a67f8a 100644 --- a/vllm/v1/worker/gpu_model_runner.py +++ b/vllm/v1/worker/gpu_model_runner.py @@ -6517,11 +6517,6 @@ class GPUModelRunner( block_sizes != self._init_block_sizes or kernel_block_sizes != self._init_kernel_block_sizes ): - assert self.offload_config.uva.cpu_offload_gb == 0, ( - "Cannot re-initialize the input batch when CPU weight " - "offloading is enabled. See https://github.com/vllm-project/vllm/pull/18298 " # noqa: E501 - "for more details." - ) self._init_block_sizes = block_sizes self._init_kernel_block_sizes = kernel_block_sizes self.input_batch = InputBatch(