Open Models Almanac
Methodsinference & servinginference kernel

specific method · filed under inference & serving

FlashAttention-2

The second-generation FlashAttention implementation selected as an attention backend.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See inference kernel for the methods filed beside it.

Also called FlashAttention 2 attention implementation, attn_implementation="flash_attention_2".

sources
2
models
2
labs adopt it
2
strongest
used
↑