Freeing users from the software lottery tyranny of fused attention implementations.
Would love to see the post on nondeterminism! Think it would be a very useful resource
> My next post (~70% done) will also be about attention! This one will be a historical retrospective on why Tri Dao was the one to invent FlashAttention, and not any of the large tech companies.
looking forward to this one :).
Would love to see the post on nondeterminism! Think it would be a very useful resource
> My next post (~70% done) will also be about attention! This one will be a historical retrospective on why Tri Dao was the one to invent FlashAttention, and not any of the large tech companies.
looking forward to this one :).