implementation detail · not yet filed
AITER fused-MoE backend
Also called VLLM_ROCM_USE_AITER_MOE=1.
- source
- 1
- model
- 1
- labs adopt it
- 0
- strongest
- not used
How sources treat it
One count per evidence span, weakest treatment to strongest.
not used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
set VLLM_ROCM_USE_AITER_MOE=0 to fall back to the Triton MoE kernel
not usedinference servingin vLLM