AI Briefing#pre-training
The latest AI and developer news about #pre-training, with the original source and a short summary.
The latest AI and developer news about #pre-training, with the original source and a short summary.
The move would mark the first time Ascend chips are used for full pre-training, following a September 2026 release of open-source infrastructure components adapted for the platform.
DeepSeek V5 is planned to be pre-trained on Huawei Ascend chips, marking the first time a top-tier Chinese model uses domestic hardware for this phase.
Trained on 16,000 GB200 GPUs for 38 days with 50T tokens, claiming 4–12x compute efficiency improvement over DeepSeek-V4-Pro-Base
This explains the relationship between AI, LLMs, and ChatGPT, along with the standards for model training and selection.
The first development log for Kanana-2 summarizes the key decisions made during the pre-training stage.
Kakao's Kanana Essence, trained on 3T tokens, achieved higher benchmark averages than llama-3.1-8b, while Kanana Nano maximized efficiency through pruning and distillation techniques.