Uint8 and Int8 quantization handling as a compiler pass

[CharlieL7]

• Currently we only handle int8 mixed precision, uint8 activations and int8 weights, in GEMMS in the parser.
• There needs to be an update that adds a pass or updates simplify_qdq to do the same for convolutions and handle all the cases.
• Got a test model from CK that sees this problem: https://drive.google.com/file/d/12vygauV8sdP19ooBTx7BnxurY3iPVQ1l/view?usp=drive_link