[jbochi]

Pretty cool. Shameless plug: My team at Anthropic is hiring people that can write accelerator kernels. Please reach out to <my username>@gmail.com if you want to make state of the art models faster :)

[trashtensor]

not looking for a job at this time but i do this kind of work - what is the name of the team that you are working on / typically works on this?

[winwang]

Curious, do you guys use Triton? I was surprised to find out PyTorch slowdown is palpable even compared to basic CUDA kernels.

[petermcneeley]

qq: Would this be in CUDA?

[jbochi]

Not sure what I can share publicly, but we use TPUs as well: https://cloud.google.com/blog/products/compute/announcing-cl...

[fpgamlirfanboy]

It's funny - former Google devs (whom I just maintain a good relationship with their former employer) are ideally positioned to profitably take advantage of the arb of TPU over GPU.

[bee_rider]

Google should improve their abstractions until there isn’t room for that anymore, haha.