Model techniques map
Techniquesoptimizationtraining parallelism

specific method · filed under optimization

SM-Level Context Parallelism

A context-parallel method that partitions a sequence across the SMs of a single rank and combines segment transitions to recover exact initial states.

Also called intra-device context parallelism.

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.

An automatic SM-level context-parallel (CP) planner therefore partitions the sequence across the SMs of a single rank, evaluates the segment transitions in parallel, and merges them to recover each segment’s exact initial state.

usedunclearin Kimi K3Moonshot AI

Filed alongside

Other methods under optimization :: training parallelism.