| 8 | |
| 9 | @dataclass |
| 10 | class AWQConfig: |
| 11 | ckpt: str = field( |
| 12 | default=None, |
| 13 | metadata={ |
| 14 | "help": "Load quantized model. The path to the local AWQ checkpoint." |
| 15 | }, |
| 16 | ) |
| 17 | wbits: int = field(default=16, metadata={"help": "#bits to use for quantization"}) |
| 18 | groupsize: int = field( |
| 19 | default=-1, |
| 20 | metadata={"help": "Groupsize to use for quantization; default uses full row."}, |
| 21 | ) |
| 22 | |
| 23 | |
| 24 | def load_awq_quantized(model_name, awq_config: AWQConfig, device): |
no outgoing calls
no test coverage detected
searching dependent graphs…