DeepSeek V2 Breakthroughs Sparsity, RL, and Expert Distillation for Peak Reasoning
7:14
DeepSeek V2 Breakthroughs Sparsity, RL, and Expert Distillatio…
23 views2 months ago
YouTubeAINexLayer
DeepSeek v3.2 Exp introduces DeepSeek Sparse Attention (DSA) and if it works out, it will be a huge
1:18
DeepSeek v3.2 Exp introduces DeepSeek Sparse Attention (DSA) …
639 views2 months ago
YouTubeEd Honour
练习两天半，完全从零开始实现DeepSeek Sparse Attention（DSA，DS-V3.2-Exp），从原理讲解到代码训练全流程，你一定要看-偷星九月333-偷星九月333-哔哩哔哩视频
练习两天半，完全从零开始实现DeepSeek Sparse Attention（DSA…
2 months ago
bilibili.com
[DSA] DeepSeek Sparse Attention. Boosting Long-Context Efficiency with DeepSeek-V3.2-Exp DSA | Byte Goose AI
[DSA] DeepSeek Sparse Attention. Boosting Long-Context Efficiency …
103 views1 month ago
linkedin.com
How to make your CPU as fast as a GPU - Advances in Sparsity w/ Nir Shavit
How to make your CPU as fast as a GPU - Advances in Sparsity w/ Nir …
51.6K viewsSep 17, 2022
YouTubeYannic Kilcher
【人工智能】DeepSeek V3 53页技术报告快速解读 | 性能表现卓越 | 架构创新 | MLA | MoE架构 | DualPipe | 预训练 | 超参数设置 | MTP | 后训练
12:44
【人工智能】DeepSeek V3 53页技术报告快速解读 | 性能表现卓越 | 架 …
71.2K viewsDec 31, 2024
YouTube最佳拍档
【人工智能】DeepSeek发布新模型V3.2-Exp | 全新DSA稀疏注意力机制 | 闪电索引器 | 长上下文效率优化 | 细粒度的token选择 | MLA架构 | 密集预热+稀疏训练 | 蒸馏
20:08
【人工智能】DeepSeek发布新模型V3.2-Exp | 全新DSA稀疏注意力机制 …
13.2K views4 months ago
YouTube最佳拍档
42:16
【AI大模型课程】DeepSeek V3.2 Exp革命性架构：稀疏注意力 + DS…
526 views4 months ago
YouTube人工智能AI课堂-卢菁博士(北大)
58:20
【deepseek从入门到精通】deepseek-v3详解：deepseek本地部署 零成本 …
218 views4 months ago
YouTubeDr.LuAIclass 卢菁 北大博士后 AI 专家
2:45
DeepSeek Sparse Attention Explained
2.6K views4 months ago
YouTubeCloud with Karl
6:16
Intro to SparseZoo
399 viewsMar 7, 2023
YouTubeNeural Magic
7:37
DeepSeek-V3.2: How "Sparse Attention" Broken the Compute B…
42 views2 months ago
YouTubeEngineering TL;DR
8:56
DeepSparse - Enabling GPU Level Inference on Your CPU
534 viewsOct 20, 2023
YouTubeFahd Mirza
15:00
NEW DeepSeek Sparse Attention Explained - DeepSeek V3.2-Exp
2.2K views4 months ago
YouTubeVuk Rosić
23:40
Automated ML Deployment using OctoML with Vanessa Yan
378 viewsOct 11, 2022
YouTubeUltralytics
0:23
🧐👉 DeepSeek放大招！新技術讓AI運算成本直接砍半，效能還不減 #QixNew…
1.1K views4 months ago
YouTubeQixNews 快克新聞
0:58
YOLOv5 on CPUs: Sparsifying to Achieve GPU-Level Performance a…
7.3K viewsAug 6, 2021
YouTubeNeural Magic
42:27
Unlock Faster and More Efficient LLMs with SparseGPT
2.7K viewsMay 26, 2023
YouTubeNeural Magic
0:38
YOLOv3 on the Edge: DeepSparse Engine vs. PyTorch
2.1K viewsMay 25, 2021
YouTubeNeural Magic
15:10
[DeepSeek Sparse Attention] DeepSeek. Boosting Long-Contex…
173 views1 month ago
YouTubeAI Podcast Series. Byte Goose AI.
59:10
How to Achieve the Fastest CPU Inference Performance for Object …
3.8K viewsJul 21, 2022
YouTubeNeural Magic
1:06
5x Faster YOLOv8 on CPUs
4.8K viewsJul 12, 2023
YouTubeNeural Magic
The official Red Hat blog
May 1, 2024
redhat.com
11:16
解读DeepSeek最新论文：Native Sparse Attention
411 views11 months ago
bilibili硅基布衣慕容康
0:27
We’ve developed the Sparse Transformer, a deep neural networ…
7.9K viewsApr 23, 2019
FacebookOpenAI
1:03
deep learning depth prediction comparsion
401 viewsSep 14, 2020
bilibili-YEAH-
0:57
DeepSeek V3.2 核心技术创新--DeepSeek Sparse Attention
62 views2 months ago
bilibiliLLM讲师
1:40
deepseek官方出品，集成方案全集，一次性看完
144 views1 year ago
bilibililiu6105
8:01
成本暴降50%！deepseek3.2重磅发布！架构大突破，原论文剖析+详解模 …
1.5K views4 months ago
bilibili赋范课堂
32:47
目前B站最全最细的DeepSeek大模型保姆级教程，DeepSeek R1本地部 …
137.7K viewsFeb 12, 2025
bilibili图灵学院官方
See more videos
Static thumbnail place holder