Step-3.7-Flash
StepFun--attention-backend trtllm_mha
usedsoftware implementationin Step 3.7 Flash NVFP4StepFun
1 more from this model
--attention-backend trtllm_mha
usedsoftware implementationin Step 3.7 Flash NVFP4StepFun
implementation detail · filed under inference & serving
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.
2 quotes from 2 sources, one card per model, each opening with its strongest.
--attention-backend trtllm_mha
--attention-backend trtllm_mha