
Fuse-All MoE kernel speeds TPU LLM inference by up to 34% with load balancing
Researchers unveiled Fuse-All MoE, a TPU kernel that fuses expert computation and output routing.
Try in Readermixture-of-expertstpuinferenceload-balancing
The AI news that matters for people who make things — what happened, and how to put it to work in Grafy.