Run DeepSeek-R1 Dynamic 1.58-bit
unsloth.ai/blog/deepseekr1-dynamic
Feb 14, 2025
1
通义阅读助手_AI速读超长文档_通义tongyi.ai-通义千问
tongyi.aliyun.com/efficiency/doc/read?taskId=4466930
Feb 13, 2025
2
NVLink 原理剖析
chenzomi12.github.io/02Hardware04NVIDIA/05DeepNvlink.html
Jan 15, 2025
1
Ethernet-Based GPU Scale-UP Networks
www.fibermall.com/blog/ethernet-based-gpu.htm
Dec 9, 2024
1
AIGC承载网优化设计方案（下）
asterfusion.com/blog20230814-aigc-1-2/
Oct 10, 2024
1
Etched is Making the Biggest Bet in AI
www.etched.com/announcing-etched
Sep 27, 2024
8
HotChip2024后记: 谈谈加速器互联及ScaleUP为什么不能用RDMA
omnivore.app/lonelygo/hot-chip-2024-scale-up-rdma-191c02ec5af
Sep 5, 2024
1
llm-inference-benchmark/LLM推理优化.md at main · ninehills/llm-inference-benchmark
github.com/ninehills/llm-inference-benchmark/blob/main/LLM%E6%8E%A8%E7%90%86%E4%BC%98%E5%8C%96.md
Aug 26, 2024
1
数据中心的暗战
zhuanlan.zhihu.com/p/331804131
Aug 22, 2024
6
聊一聊CXL
zhuanlan.zhihu.com/p/466870704
Aug 9, 2024
9
谈一下ucie
zhuanlan.zhihu.com/p/480232426
Aug 9, 2024
1
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