T
traeai
Sign in

模型

Kimi K2

别名:kimi-k2

由Kimi开发的模型,采用first_k_dense策略。

已跟踪 2 条高相关材料

TraeAI 观察

相关材料

已收录 2 条与 Kimi K2 相关的内容,按评分排序。

DeepSeek V4的tid2eid是怎么来的?

How is the tid2eid in DeepSeek V4 Generated?

科学空间3057 字 (约 13 分钟)
75

The article explores the generation mechanism of the tid2eid mapping table in the DeepSeek V4 model.

入选理由:DeepSeek V4采用hash routing替代first_k_dense策略

FeaturedArticle#Deep Learning#Model Architecture#MoE中文
Training Kimi K2 and Qwen3 30B-scale models efficiently requires more than standard data-parallel tr...

NVIDIA Megatron Core now offers end-to-end support for advanced optimizers like Muon, MOP, and REKLS, overcoming limitations of standard data parallelism to significantly accelerate training of 30B-scale models such as Kimi K2 and Qwen3 on GB300 and NVL72 systems.

入选理由:传统数据并行已不足以高效训练30B+大模型,需引入高阶优化器。

FeaturedTweet#NVIDIA Megatron Core#Muon#Qwen3#Kimi K2#LLM Training Optimization英文

跨材料问答 · Kimi K2

回答基于:Kimi K2 相关 2 条材料
    0 / 500

    AI may generate inaccurate information. Please verify important content.