thom✨

@levidiamode @charles_irl looks cool man

Day 74/365 of GPU Programming I always found die shots and SM diagrams beautiful but difficult to map mentally, so I've been trying to find a way to interact with GPUs in 3D. This is what I have so far: a single input that goes through a simplified H100 execution pipeline to see what the silicon is doing at each step; from CPU-side tokenization and embedding lookup, through matmuls on tensor cores to the final softmax output. My current plan is to make this an interactive playground that lets you zoom in and zoom out through various levels of depth (package → die → GPC → SM → tensor core) while also including step-through examples similar to the bycroft LLM 3D visualization. Ideally this should make exploring the architectural side just as easy as mapping CUDA abstractions onto the actual hardware processes. I'm starting with an H100 but would be fun to expand this to more GPUs and highlight the differences between generations. This was largely inspired by @srush_nlp's GPU puzzles, @JayAlammar's Illustrated Transformers and @karpathy's makemore series, which made me think about how to study and visualize GPUs from the ground up.

@LLCoolChris_ 🙅‍♂️ matrices 👍ia

Aïe aïe aïe

@gpusteve i always see emilio’s posts on linkedin and i love your thumbnails

wanted to write a bit about some a pitfall we ran into when using cpp_extensions.load() for our kernel generation benchmarks. you can easily lose a few microseconds if you're not pinning processes correctly or loading too many modules.

Jensen’s self described “best slide”

oh the keynote is still live lets go

blog post on division in SASS thom.gg/division

cover and opener for Bloomberg Businessweek.

@beffjezos @PrimeIntellect @willccbb where is that why is it happening in a church its beautiful

The one and only @willccbb walking the crowd through the @PrimeIntellect stack and continual learning concepts

@AKirtesh @Hi_Mrinal wdym interview on resume lmao

@Hi_Mrinal xAI interview on the resume >>> most people's dream offers. King shit fr 😌👀

Still one of my biggest fumble

BTW if you agree with this, you don't work on difficult enough problens

@teodorio blessed

I never did a leetcode problem

@TimurNegru its quite in the middle of nowhere tho

Someone is selling an 18th-century French estate sitting directly on the Lot River. 27 rooms, 10 beds/8 baths, 487m² (5,200 sq ft) of living space across the main house and 3 gîtes (self-contained guesthouses). 2 swimming pools, tennis court, wine cellar and 1.18 hectares (2.9 acres) of gardens running down to the river. Live in the main house, your friends and family have their own space and nobody's in each other's way. This is Cahors Malbec country by the way, with Bordeaux 2,5 hours away (wine lovers will understand). Asking price: €1.3M ($1.4M). How much would an estate like this cost in your country?

wtf is a MUFU.RCP

American Companies: Hyper-Fixated on ending privacy. European Companies:

@AviSchiffmann cant deny it did make some noise on french twitter

its the week end me and claude are reading SASS !

@5amoljen its a great lab for ai research?

I got an offer from CERN :)

new blog and new blog post thom.gg/fighting-cubla…

@Leik0w0 if you had no gpus what would u use, prime intellect to rent them?

Couldn’t agree more, there is absolutely no requirement for building an expensive homelab to learn kernel programming.