Gahow Wang ad82e8bf92 dist: lengthen scaling bench so NCCL init amortizes ...

30-step bench charged the one-time NCCL init + 4 model builds (present at world=4,
absent at world=1) against the wall clock, understating steady-state scaling
(in-loop tok/s already showed ~53k at 4 GPUs). Bump to 150 steps.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-15 17:18:23 +08:00

..

ddp_correctness.rs

dist: lengthen scaling bench so NCCL init amortizes

2026-06-15 17:18:23 +08:00