
又被打脸了,apple M1 ultra
zhuanlan.zhihu.com/p/482450390
Aug 9, 2024
1

GTC的热点,不凑一下那是犯罪
zhuanlan.zhihu.com/p/487389526
Aug 9, 2024
14

再凑一下壁仞的热点……
zhuanlan.zhihu.com/p/558798037
Aug 9, 2024
3

关于Spatial Computing
zhuanlan.zhihu.com/p/463833198?utm_psn=1743335463325310977
Jul 31, 2024
19

nvlink那些事……
zhuanlan.zhihu.com/p/639228770
Jul 31, 2024
8

AI DC的参数面互联最优解是OXC吗?
zhuanlan.zhihu.com/p/629283582
Jul 26, 2024
4

LLM推理到底需要什么样的芯片?(2)
zhuanlan.zhihu.com/p/683908169
Jul 25, 2024
1

LLM推理到底需要什么样的芯片?(1)
zhuanlan.zhihu.com/p/683359705
Jul 25, 2024
1

scale up域的拓扑
zhuanlan.zhihu.com/p/708991795
Jul 24, 2024
3

站在AI Scale-Up域的一个岔路口
zhuanlan.zhihu.com/p/707355769?utm_psn=1796087465674674176
Jul 23, 2024
3

AI fabric is a bus or a network?
zhuanlan.zhihu.com/p/708602042
Jul 23, 2024
2

大模型推理分离架构五虎上将
zhuanlan.zhihu.com/p/706218732
Jul 22, 2024
4

为Token-level流水并行找PMF:从TeraPipe,Seq1F1B,HPipe到PipeFusion
zhuanlan.zhihu.com/p/706475158
Jul 22, 2024
1

LLM分离式推理可能带来的软硬件变革的迷思
zhuanlan.zhihu.com/p/707199343
Jul 22, 2024
1

GB200 Hardware Architecture - Component Supply Chain & BOM
www.semianalysis.com/p/gb200-hardware-architecture-and-component
Jul 17, 2024
3

Mooncake (1): 在月之暗面做月饼,Kimi 以 KVCache 为中心的分离式推理架构
zhuanlan.zhihu.com/p/705754254
Jul 12, 2024
3
AI Inference — 从前沿技术到商业化实操观察 (社区版) - 飞书云文档
miracleplus.feishu.cn/docx/Lqe1dgVTho0vEVxZqLZcFpmgnkb
Jul 10, 2024
1

From bare metal to a 70B model: infrastructure set-up and scripts
imbue.com/research/70b-infrastructure/
Jul 3, 2024
1

星融元针对LLM大模型承载网发布星智AI网络解决方案
asterfusion.com/a20240205-ai-llm-solution/
Jun 13, 2024
4

云原生机器学习平台技术综述(编排调度篇)-来也科技
laiye.com/news/post/2627.html
May 20, 2024
1
DeepSpeed/blogs/deepspeed-fastgen/2024-01-19 at master · microsoft/DeepSpeed
github.com/microsoft/DeepSpeed/tree/master/blogs/deepspeed-fastgen/chinese
May 20, 2024
8

Nvidia Blackwell Perf TCO Analysis - B100 vs B200 vs GB200NVL72
www.semianalysis.com/p/nvidia-blackwell-perf-tco-analysis
May 11, 2024
2

在生产环境中的OpenStack上运行Kubernetes集群 - 墨天轮
www.modb.pro/db/47575
May 9, 2024
2

OpenStack与K8s的关系 OpenStack与Kubernetes(K8s)的区别
www.usa-idc.com/news/idc/2023071414.shtml
May 9, 2024
1