q10

/

Qwen3-8B-Base-INT8-INT4

like 0

• "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
• "torch._utils._rebuild_wrapper_subclass",
• "torch.int8",
• "torch.CharStorage",
• "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
• "torch.bfloat16",
• "torch._utils._rebuild_tensor_v2",
• "collections.OrderedDict",
• "torch.serialization._get_layout",
• "torchao.dtypes.uintx.q_dq_layout.QDQTensorImpl",
• "torchao.dtypes.uintx.q_dq_layout.QDQLayout",
• "torch.device",
• "torch._tensor._rebuild_from_type_v2",
• "torchao.quantization.quant_primitives.ZeroPointDomain",
• "torch.BFloat16Storage",
• "torchao.quantization.quant_api._int8_asymm_per_token_quant"

How to fix it?