Open Models Almanac
Methodsinference & servinginference kernel

implementation detail · filed under inference & serving

TensorRT-LLM multi-head attention backend

The TensorRT-LLM multi-head attention backend selected through the trtllm_mha attention-backend setting.

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 trtllm_mha, trtllm_mha attention backend.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2
↑