
英伟达GB200架构解析:互联架构和未来演进-电子工程专辑
www.eet-china.com/mp/a301182.html
Apr 8, 2024
5

暴力美学的优雅化——NVidia的Rack Scale
zhuanlan.zhihu.com/p/689424234
Apr 8, 2024
1

英伟达AI芯片路线图分析与解读
wallstreetcn.com/articles/3712058
Apr 7, 2024
2

GPT-4 “炼丹”指南:MoE、参数量、训练成本和推理的秘密
www.aixinzhijie.com/article/6825966
Apr 2, 2024
4

英伟达 A100知识分享 GPU 板组单机价值量 1.2 万
www.jaeaiot.com/news/detail/32.html
Feb 22, 2024
3

SemiAnalysis | Dylan Patel | Substack
www.semianalysis.com/p/groq-inference-tokenomics-speed-but?utm_source=post-email-title&publication_id=329241&post_id=141888751&utm_campaign=email-post-title&isFreemail=true&r=b0aiz&utm_medium=email
Feb 22, 2024
1

Accelerating Generative AI with PyTorch II: GPT, Fast
pytorch.org/blog/accelerating-generative-ai-2/
Jan 22, 2024
1

How Nvidia’s CUDA Monopoly In Machine Learning Is Breaking - OpenAI Triton And PyTorch 2.0
www.semianalysis.com/p/nvidiaopenaitritonpytorch
Jan 22, 2024
9

GPU 进阶笔记(一):高性能 GPU 服务器硬件拓扑与集群组网(2023)
arthurchiao.art/blog/gpu-advanced-notes-1-zh/
Jan 8, 2024
1

TPUv5e: The New Benchmark in Cost-Efficient Inference and Training for <200B Parameter Models
www.semianalysis.com/p/tpuv5e-the-new-benchmark-in-cost
Dec 28, 2023
3

DSA的翻身路
zhuanlan.zhihu.com/p/626287371
Dec 26, 2023
2

数一数英伟达黄家刀法欠缺的招式——(上篇)
zhuanlan.zhihu.com/p/642260820
Dec 26, 2023
6

谈一下英伟达帝国的破腚
zhuanlan.zhihu.com/p/639181571
Dec 20, 2023
3

NLP(二十):漫谈 KV Cache 优化方法,深度理解 StreamingLLM
zhuanlan.zhihu.com/p/659770503
Oct 11, 2023
1

疯狂的 H100:现代 GPU 体系结构浅析,从算力焦虑开始聊起
zhuanlan.zhihu.com/p/659738090?utm_psn=1693972042385416192
Oct 9, 2023
2

FlashAttention2详解(性能比FlashAttention提升200%)
zhuanlan.zhihu.com/p/645376942
Oct 8, 2023
3

分析transformer模型的参数量、计算量、中间激活、KV cache
zhuanlan.zhihu.com/p/624740065
Sep 12, 2023
1

图解GPT-2 | The Illustrated GPT-2 (Visualizing Transformer Language Models)_Ann's Blog的博客-CSDN博客
blog.csdn.net/qq_36667170/article/details/125529598?spm=1001.2014.3001.5501
Sep 8, 2023
2

解析 Transformer 模型 | Way to AGI
blog.waytoagi.com/article/transformer_explained
Sep 7, 2023
5

PyTorch 2.0
pytorch.org/get-started/pytorch-2.0/
Sep 4, 2023
2