I regret building a $3000 Pi AI Cluster скачать в хорошем качестве

I regret building a $3000 Pi AI Cluster

It's been a while. Some Kickstarters take time. What do you think about doing the same thing 10 times in a row, over and over? If that's your jam, build a cluster like I did in this video! If you want to replicate the Compute Blade Cluster, here are all the parts I used (some links are affiliate links): Compute Blade DEV:   pishop.us/product/compute-blade-dev/   Compute Blade Standard Fan Unit:   pishop.us/product/fansta-1v1-0/   Compute Blade 10" 3D Print Rackmount:   github.com/uptime-lab/compute-blade/tree/m...   Raspberry Pi CM5 16GB (CM5016000):   pishop.us/product/raspberry-pi-compute-mod...   GLOTRENDS Aluminum CM5 Heatsink:   amzn.to/45yacbv   Patriot P300 256GB NVMe SSD 10-pack:   amzn.to/4lpj0jc   GigaPlus 2.5 Gbps 10 port PoE+ switch:   amzn.to/3unowsd   GigaPlus 10" Rack Mount 3D Print ears:   printables.com/model/1215585-unified-10-ra...   Monoprice Cat6A SlimRun 6" Cat6 patch cables (10 pack):   amzn.to/4fx1gzr   ioplex SFP+ Twinax DAC patch cable:   amzn.to/47ulpkx   DeskPi RackMate TT:   amzn.to/3uujchp   Other resources mentioned in the video: My older Compute Blade video:    • ARM yourselves! The Compute Blade is here.   Xerxes Pi Kickstarter:   kickstarter.com/projects/1907647187/small-...   Xerxes Pi testing:   github.com/geerlingguy/raspberry-pi-pcie-d...   Unredacted Labs' Tor exit cluster:   unredacted.org/blog/2025/05/unredacted-labs/   World's Largest Pi Cluster at UC Santa Barbara:   independent.com/2025/04/29/worlds-biggest-...   Support me on Patreon:   / geerlingguy   Sponsor me on GitHub:   github.com/sponsors/geerlingguy   Merch:   redshirtjeff.com   2nd Channel:    / @geerlingengineering   3rd Channel:    / @level2jeff   Contents: 00:00 - 2 years 2 long 00:32 - Another blade 01:30 - Unboxing a cluster 03:06 - Assembling one of 10 06:11 - A bandolier of microSD cards 07:16 - Assembling blades 2-10 08:16 - Next steps - fans and storage 10:17 - Flashing NVMe drives 11:00 - Only Fan Units 12:45 - They all just... disappeared 14:33 - Spending another $200 15:45 - Cluster benchmarks: HPL 16:23 - Spending another $70 17:03 - Framework cluster vs Pi cluster 18:12 - AI clustering (down one node) 19:26 - llama.cpp is totally RPC 20:54 - Exo and Distributed Llama 22:09 - Blade (the movie) vs blade (the compute)