[NeurIPS 2023] Softmax Output Approximation for Activation Memory-Efficient Training of Attention...

59 views

Embedded AI Lab, UNIST

8 days ago

[NeurIPS 2023] Softmax Output Approximation for Activation Memory-Efficient Training of Attention...

[NeurIPS 2023] Softmax Output Approximation for Activation Memory-Efficient Training of Attention...