Rejected 27 Times, He Built PyTorch. Keep going

#DeepLearning with PyTorch... 1) Cheat sheet [PDF]: https://t.co/TcRqfgrdEi 2) Learn fundamentals with hands-on coding [PDF]: https://t.co/IsXFjwW86S 3) #GenerativeAI with Python and PyTorch: https://t.co/hfbERRkGZ2 book v/ @PacktDataML

I vibecoded this neural network visualization for my students and open sourced it. It shows a simple MLP trained on MNIST handwritten digits at several training steps. The visualization is using @threejs and it comes with training code in @PyTorch . Link + repo 👇

If you feel like giving up, you must read this never-before-shared story of the creator of PyTorch and ex-VP at Meta, Soumith Chintala. > from hyderabad public school, but bad at math > goes to a "tier 2" college in India, VIT in Vellore > rejected from all 12 universities for

Pytorch version of the book 'Hands on machine learning' just came out. those reading the tensorflow & keras version, do check it out :) link to original post 👇

simple NVFP4 quantization within 100 lines of pytorch

Curious how frameworks like nanochat actually scale? New blog post: Introduction to Parallelism in PyTorch. Covers async DDP, ZeRO-1/2, FSDP, and TP – with implementations from scratch and practical advice from real runs on different hardware. Even if you are experienced,

The creator of GPT doesn’t have a PhD. The creator of PyTorch doesn’t have a PhD. The research lead at Cursor dropped out of NEU. You don’t need a PhD or a top school to become a great researcher or engineer. You can just do things!

[ENG SUB] how it feels to use eager pytorch in 2025

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through

Copy-pasting PyTorch code is fast — using an AI coding model is even faster — but both skip the learning. That's why I asked my students to write by hand ✍️. 🔽 Download: https://t.co/tMWgeYKzz9 After the exercise, my students can understand what every line really does and

[ML Grind] My main focus these days is mastering pytorch and making progress on the ml for bio projects. Here is the breakdown of things I've been doing to achieve those two: > Building simple projects from scratch in pytorch > Rebuilding my healthcare project from keras to

PyTorch version of Hands-On Machine Learning Book by Aurélien Géron is just out! This was one of my favorite books when I started learning machine learning and it's nice to see it using PyTorch. Data science courses/MOOCs back then used to teach you numpy, pandas, matplotlib,

Linux Kernel Architecture 🚀 As the demand for computing resources for modern AI continues to rise, the SYSTEM-LEVEL skill set is becoming increasingly important. Many practitioners jump straight to the application layer (like PyTorch, GPU/CUDA) and treat the underlying

Leaving Meta and PyTorch I'm stepping down from PyTorch and leaving Meta on November 17th. tl;dr: Didn't want to be doing PyTorch forever, seemed like the perfect time to transition right after I got back from a long leave and the project built itself around me. Eleven years

PyTorchリードのソウミスさんMeta退社 当時天下のGoogle TensorFlowに対して「今更後発？」と半信半疑だった事を覚えてます ・ニ番手大学出身数学苦手 ・修士27校応募26校不合格 ・Google DeepMind3回不合格 ・Meta入社時は極度の自信喪失 ・社内政治に潰されかける 神が試した感ある波乱万丈で感動

Hybrid models like Qwen3-Next, Nemotron Nano 2 and Granite 4.0 are now fully supported in vLLM! Check out our latest blog from the vLLM team at IBM to learn how the vLLM community has elevated hybrid models from experimental hacks in V0 to first-class citizens in V1. 🔗

last night : - implemented linear regression using Pytorch's high level API - implemented a regression MLP - implemented a mini batch gradient decent using dataloaders today : - will evaluate the model - build nonsequential models using custom loaders - implement models with

Below are few popular Python libraries explained in brief : - NumPy: fast math & arrays. - Pandas: data analysis. - Matplotlib/Seaborn: charts. - SciPy: scientific computing. - Scikit-learn: machine learning. - TensorFlow/Keras/PyTorch: deep learning. - Flask/Django: web apps.