It’s pretty much neutral for me also aha, and yeah I meant running up one of several TPUs of several servers of several pods of several clusters of my region’s copy of Google Gemini.
I did a bit of research on the scale of Gemini
As of last year, each TPU has 32GB of HBM VRAM; there are 8 TPUs in a host server; 32 hosts in a ‘pod’; in a mid-sized Europe hub of which there are several dozen, around 24 pods make up an inference cluster, which does one of image generation, coding etc.; several inference clusters in a regional cluster, and that is Gemini. Each regional cluster/hub around the world is essentially a livesynced copy of a Gemini instance.
The EU hub I researched had, last year, the rough equivalent of 250TB of VRAM and 1.4PB of system RAM.
At what cost are you willing to accept the improvement?
Disclaimer
Because this was modified with Gemini AI, using that comment alone as the prompt.
Apparently at the cost of an entire town’s water supply and several tons of carbon emissions… 🙄
But if you’re referring to the speech bubble having two lines, one of them in the original did anyway so that’s a net neutral
It’s pretty much neutral for me also aha, and yeah I meant running up one of several TPUs of several servers of several pods of several clusters of my region’s copy of Google Gemini.
I did a bit of research on the scale of Gemini
As of last year, each TPU has 32GB of HBM VRAM; there are 8 TPUs in a host server; 32 hosts in a ‘pod’; in a mid-sized Europe hub of which there are several dozen, around 24 pods make up an inference cluster, which does one of image generation, coding etc.; several inference clusters in a regional cluster, and that is Gemini. Each regional cluster/hub around the world is essentially a livesynced copy of a Gemini instance.
The EU hub I researched had, last year, the rough equivalent of 250TB of VRAM and 1.4PB of system RAM.
WE MUST FIX IT AT THE COST OF ALL OUR LIVES