Skip to content

397B v7x RL trainer: GDN kernel, MoE routing and engine speedups (10.62 -> 9.80 s per micro-batch on the 128-chip bench) - #5759

Closed
khatwanimohit wants to merge 11 commits into
atwigg/mlperffrom
mohit/trainer-perf-v7x
Closed

397B v7x RL trainer: GDN kernel, MoE routing and engine speedups (10.62 -> 9.80 s per micro-batch on the 128-chip bench)#5759
khatwanimohit wants to merge 11 commits into
atwigg/mlperffrom
mohit/trainer-perf-v7x

Commits

  1. Commits on Oct 15, 2026