specific method · filed under inference & serving
Expert parallelism
Distributes MoE experts across parallel workers; the evidence identifies it as a way to improve throughput.
Also called enable expert parallelism.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- optional
How sources treat it
One count per evidence span, weakest treatment to strongest.
optional 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Enable expert parallelism with --enable-expert-parallel to improve throughput.
optionalinference servingin Qwen3.8-Flash-NextvLLM recipe authors
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 encodingFused 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 layersTensorRT-LLM all-reduce backendToken migration for balanced expert placement