tensor parallelism

2 statements across 1 episodes · 0 bullish · 2 bearish · 2 people on the record · first statement Aug 3, 2026 by Philip Kiely · across every show →

Everything said about tensor parallelism, oldest first

Aug 3, 2026 bearish
Insight
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…”
Philip Kiely Aug 3, 2026 ▶ 51:29 Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten
Aug 3, 2026 negative
Insight
Fused GPU kernels cannot eliminate inter-GPU communication in tensor parallelism
“Well, I mean, like a fused kernel can't save you. Like here with the tensor parallelism, you're the half, the matrix is one GPU and the other half is on another. And if I need the entire matrix in order to do like a non-linear operation on the next step, which…”
Ali Taha Aug 3, 2026 ▶ 57:38 Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.