| 13 | |
| 14 | @register_model('fla') |
| 15 | class FlashLinearAttentionLMWrapper(HFLM): |
| 16 | def __init__(self, **kwargs) -> FlashLinearAttentionLMWrapper: |
| 17 | |
| 18 | # TODO: provide options for doing inference with different kernels |
| 19 | |
| 20 | super().__init__(**kwargs) |
| 21 | |
| 22 | |
| 23 | if __name__ == "__main__": |
nothing calls this directly
no outgoing calls
no test coverage detected