Calculating and achieving peak TOPS on the DGX Spark
You’ll often see “peak TOPS” advertised for accelerators like GPUs - but where does that number come from, and can we achieve it? Let’s break it down using the DGX Spark’s 1000 TOPS as an example.
My blog on software, productivity, and obsessively optimizing. I work at Google, ex-Zillow. Thoughts my own.
You’ll often see “peak TOPS” advertised for accelerators like GPUs - but where does that number come from, and can we achieve it? Let’s break it down using the DGX Spark’s 1000 TOPS as an example.
Like many, I’ve started to get really bullish on the future of local LLMs - the open models and weights are getting better every few weeks. Qualitatively, I think it’s still abundantly clear that local LLMs are not at par with the larger hosted models for my high-priority use cases like coding.
Problem
The main concern I have with allow_missing is duplication. Does it overlap with some existing api, such as the new apply method?
This document serves as a corrolary to this issue on aep.dev, including my thoughts to remove the soft delete pattern.
I’ve started a video series on agentic coding, and you can view the first video here. This is a short summary if you prefer a post instead!
The new AI Era
Data Uniqueness via Gradient Similarity
Setting up Hibernate on Linux
This is are some notes about what I eat, how I eat, and why.