implementation detail · filed under inference & serving
TensorRT-LLM all-reduce backend
Selects TensorRT-LLM as the all-reduce backend.
Also called trtllm all-reduce backend.
- 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.
export VLLM_FLASHINFER_ALLREDUCE_BACKEND=trtllm
usedinference servingin vLLMNVIDIA
Filed alongside
Other methods under inference & serving :: serving parallelism.
Attention data parallelismDeepEPPrefill-decode disaggregationEncoder-Prefill-Decode disaggregationTensor parallelism (degree 4)Tensor parallelism (degree 8)Topology-aware NVLink domain placementZero-copy fused token permutation and unpermutationData-parallel vision encodingExpert parallelismFused reduce-scatter/all-gather collectivesIdentical cache-layout pinning across prefill and decode poolsLow-precision MoE combineRound-robin routing for prefill-decode disaggregationTensor parallelism for MoE layersToken migration for balanced expert placement