Re:FlashAttention-T: Towards Tensorized Attention
by cs702 on Thursday February 05, 2026 @10:30AM
(#46900745)
I'd add this to the list of linear-attention RNNs:
https://arxiv.org/abs/2602.00294
Recently saw it on HN.
It's so annoying. Transformers keep improving and recurrent networks are harder to train so until we hit some real wall, companies don't seem eager to diverge. It's like lithium batteries improving easy faster than it was profitable to work on sodium ones, even though we unfortunately want the sodium ones to be better.