From 46M to 325M: An Inference NPU Now Pretrains a Language Model at GPU Quality
This story is from 2026-10-29. It is preserved in the archive; the latest stories are on the live feed.
TL;DR Two weeks ago we wrote about VKORE-46M, a small model pretrained on an inference-only NPU. VIDRAFT has now scaled the same idea seven times: VKORE-325M-NPU-Base , a 325.6M-parameter language model pretrained from random initialization on a Rebellions ATOM-Max , a commercial inference NPU. A t…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-29 08:02 · DEV Community — Machine Learning
From 46M to 325M: An Inference NPU Now Pretrains a Language Model at GPU Quality