nowfound

Dev tools · July 10, 2025

Trim Transformer: A transformer for physics models

Trim is building a foundation model for physics. We found almost all well-maintained transformer-based architectures are optimized for language models. We’re releasing our own open-source transformer package that is optimized for physics. It achieves a 90% reduction in memory usage and a 3.5x speedup in a standard Navier-Stokes dataset.

Trim Transformer: A transformer for physics models launched on July 10, 2025 with 10 votes, #2,392 of 9,223 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.

In plain words

Trim Transformer is an open-source transformer package designed specifically for physics models rather than language processing. The software reduces memory usage by 90% and increases speed 3.5x on standard physics datasets like Navier-Stokes simulations. It addresses a gap in available transformer architectures, which are typically optimized for language tasks. The tool is intended for developers and researchers building physics-based foundation models and computational simulations.

written from the facts on this page · September 2026

From the sources

A linear attention transformer package. Contribute to eg-trim/trim-transformer development by creating an account on GitHub.

trim-transformer is a lightweight PyPI package that replicates the familiar interface of torch.nn.TransformerEncoder , but with an attention function of the form Attn(Q,K,V) = QK^TV, which we call multi-linear attention. This implementation has time complexity O(nd^2), where n is the sequence length and d is the model dimension. Since the time complexity is linear in the sequence length, this implementation is well suited for high sequence length tasks. Attention in this form has shown success in operator learning tasks, see Choose a Transformer: Fourier or Galerkin . This implementation is particularly relevent for training physics models where high sequence length can come from large grid…from github.com

Does a similar job

all alternatives →
  • IM
  • TRiP – a complete transformer engine in C built from scratch just by meApr 2026 · github.com · ▲38

    A complete transformer engine in C — inference, training, chat, vision. - carlovalenti/TRiP

  • OA
    Overfitted a 900KB Transformer to Compress a 100MB CSV into 7MBJun 2026 · ▲112

    I built an experiment that uses an overfitted transformer and arithmetic coding to compress individual files. Instead of training the model to generalize, I train a 900KB transformer to memorize a single file and predict the next byte. Those predictions are fed into an arithmetic coder to produce the compressed output. On a 100MB NYC taxi CSV, it compresses to about 7MB (~0.5 bits/byte). On a 100MB slice of enwik9, it compresses to about 21MB (~1.68 bits/byte). It's pretty slow right now (roughly 20–30 minutes of training and 45 minutes each for compression and decompression on my…

  • less than 650 LOC trainable GPT only using NumPy2023 · github.com · ▲90

    Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines). - joennlae/tensorli

  • TurboGPT: train 22KiB transformer in 13s24d ago · github.com · ▲56

    Train a tiny GPT in under a minute (CUDA only). Contribute to lostmsu/TurboGPT development by creating an account on GitHub.

  • Ideogram 4.0 – open-weight 9.3B text-to-image modelJun 2026 · github.com · ▲46

    It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https:&#x2F;&#x2F;ideogram.ai&#x2F;blog&#x2F;ideogram-4.0&#x2F; We will be happy to answer any questions :)

More dev tools this month

the category →
  • /dev/null▲490

    a social network for devs

    Dev tools · 4d ago · dev-null.sh

  • Contribute to oosexgang/hackios-xnu-kernel development by creating an account on GitHub.

    Dev tools · 18h ago · github.com

  • open-source IDE for thoughtful software design. Contribute to devdotfast/whiteboard development by creating an account on GitHub.

    Dev tools · 29d ago · github.com

  • Contribute to reladraw/reladraw development by creating an account on GitHub.

    Dev tools · 27d ago · github.com

  • OpenBot▲362

    Grok Bot alternative: free, local, open-source, multiplayer

    Dev tools · 24d ago · openbot.run

  • Talanoa▲346

    Hi HN, I’m a fullstack developer, and honestly, I’ve lost count of how many side projects I’ve worked on over the years. But one idea kept coming back to me: a different kind of email client. It first came to me in 2014: “What if we could handle emails more like conversations?” Every year, I’d revisit this concept in my “Build Notes.” Ten years later, no one had built exactly what I had in mind — so I finally decided to do it myself. That’s how Talanoa was born. I wanted something focused on people, not timelines. I was tired of marking messages as unread just to remember to reply later, or…

    Dev tools · 22d ago · talanoa.email

Source: Show HN post ↗

Launched alongside, July 2025

the whole month →
  • Clueso▲1,300

    Create stunning product videos in minutes with AI

    AI · 2025 · clueso.io

  • Hey HN! Introducing Trickle Magic Canvas: the world’s first Agentic Canvas, where you can visually co-create apps and websites with AI, from idea to production. Why is a canvas better? Most AI tools today rely on linear chats or text prompts. We believe that limits creativity and clarity. Canvas changes the game. 1. Every version & page at a glance. Each page and sub-page lives on a timeline. You can quickly browse, edit, and preview progress like a living, visual document — no more digging through chat logs or scattered states. 2. The canvas is the context. Unlike linear chats, you can…

    AI · 2025 · trickle.so

  • TB
  • Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…

    Dev tools · 2025 · nodaysoff.run

  • Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https:&#x2F;&#x2F;www.morningbrew.com&#x2F;issues&#x2F;business-buzzkill), MetaFilter (https:&#x2F;&#x2F;www.metafilter.com&#x2F;209703&#x2F;Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…

    AI · 2025 · drawafish.com

  • Hi HN - I made a site that takes a UK postcode, grabs the local MP's information and generates an AI mockup of what their ID might look like. It's a small, silly protest at the stupidity of the Online Safety Act that just came into force. edit - My open AI credits got hugged to death, please use a known postcode (like one from Kier Starmer's constituency, WC2B6NH) in the meantime.

    AI · 2025 · use-their-id.com