2025年2月26日
DeepSeek 开源记-第3天-DeepGEMM
摘要： DeepSeek 开源工作第3天 🚀 Day 3 of #OpenSourceWeek: DeepGEMM Introducing DeepGEMM - an FP8 GEMM library that supports both dense and MoE GEMMs, powering V3/ 阅读全文
posted @ 2025-02-26 15:51 bingohuang 阅读(182) 评论(0) 推荐(0)
DeepSeek 开源记-第2天-DeepEP
摘要： DeepSeek 开源工作第2天 🚀 Day 2 of #OpenSourceWeek: DeepEP Excited to introduce DeepEP - the first open-source EP communication library for MoE model traini 阅读全文
posted @ 2025-02-26 15:42 bingohuang 阅读(195) 评论(0) 推荐(0)
DeepSeek 开源记-第1天-FlashMLA
摘要： DeepSeek 开源工作第1天 🚀 Day 1 of #OpenSourceWeek: FlashMLA Honored to share FlashMLA - our efficient MLA decoding kernel for Hopper GPUs, optimized for va 阅读全文
posted @ 2025-02-26 15:37 bingohuang 阅读(150) 评论(0) 推荐(0)
DeepSeek 开源记-第0天-OpenSourceWeek
摘要： DeepSeek 在 X 上发布开源计划 🚀 Day 0: Warming up for #OpenSourceWeek! We're a tiny team @deepseek_ai exploring AGI. Starting next week, we'll be open-sourcin 阅读全文
posted @ 2025-02-26 15:08 bingohuang 阅读(28) 评论(0) 推荐(0)