Model techniques map
Techniquesinference & servinginference kernel

implementation detail · filed under inference & serving

ROCm AITER sparse MLA attention backend

A ROCm AITER backend for sparse MLA attention.

Also called --attention-backend ROCM_AITER_MLA_SPARSE.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

--attention-backend ROCM_AITER_MLA_SPARSE

usedinference servingin GLM-5.3-FlashZ.ai

Filed alongside

Other methods under inference & serving :: inference kernel.