• L
    Add feed_forward for fused attention op. (#34945) · d1a33bc7
    Li Min 提交于
    Describe
    
    Add feed_forward for fused attention op.
    (1) Encapsulate matmul impl (forward and backward) used in attention op.
    (2) Implement bias_add (forward and backward) used in attention op.
    d1a33bc7
attn_bias_add.cu.h 12.2 KB