pipeline parallelism
4 statements across 2 episodes · 1 bullish · 1 bearish · 2 people on the record · first statement Jul 29, 2024 by Eugene Cheah · across every show →
Everything said about pipeline parallelism, oldest first
Jul 29, 2024 neutral
Jul 29, 2024 positive
Aug 3, 2026
Pipeline parallelism is only necessary for multi-node AI model inference
“The only reason you would have to do pipeline parallelism which is where you separate, like, different layers, and you put, like, half the layers on one hardware and half on another, is if you are forced to do multi-node inference because a model is bigger tha…”
Aug 3, 2026 bearish
Tensor parallelism is a poor fit for local multi-device AI setups
“Tensor parallelism is not a good fit for local AI because it assumes a very high bandwidth interconnects like NVLink was, you know, They might be forced to do something like pipeline parallelism, which we're never going to do unless we're doing some kind of mu…”