MCPcopy Create free account
hub / github.com/OpenSparseLLMs/MoM / FlashLinearAttentionLMWrapper

Class FlashLinearAttentionLMWrapper

evals/harness.py:15–20  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

13
14@register_model('fla')
15class 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
23if __name__ == "__main__":

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected