GoKawiil - Latest Tech News & Aggregated Headlines

Hydrogen-Powered Plasma Torch Decimates Plastic Waste in a Blink

gizmodo.com Gayoung Lee 2025-10-14 16:30:56

Why sort plastic when you can blast it to oblivion? Sounds extreme, but that’s the idea behind a new technology with the potential to “realize the era of zero plastic sorting”—while minimizing carbon emissions, too. In a press release today, the Korea Institute of Machinery & Materials (KIMMS) announced the development of a plasma torch that annihilates plastic waste in less than 0.01 seconds—about ten times faster than a blink. The torch is entirely powered by hydrogen and converts mixed plast

Topics: hot plastic recycling torch waste

Shop Amazon

Speeding up PyTorch inference on Apple devices with AI-generated Metal kernels

news.ycombinator.com Unknown 2025-10-14 23:03:35

Speeding up PyTorch inference by 87% on Apple devices with AI-generated Metal kernels tl;dr: Our lab investigated whether frontier models can write optimized GPU kernels for Apple devices to speed up inference. We found that they can: our AI-generated Metal kernels were 1.87x faster across 215 PyTorch modules, with some workloads running hundreds of times faster than baseline. Why use AI to generate kernels for Apple devices? AI models execute on hardware via GPU kernels that define each oper

Topics: float self tensor torch uint

Shop Amazon

Speeding up PyTorch inference by 87% on Apple with AI-generated Metal kernels

news.ycombinator.com Unknown 2025-10-15 04:03:35

Speeding up PyTorch inference by 87% on Apple devices with AI-generated Metal kernels tl;dr: Our lab investigated whether frontier models can write optimized GPU kernels for Apple devices to speed up inference. We found that they can: our AI-generated Metal kernels were 1.87x faster across 215 PyTorch modules, with some workloads running hundreds of times faster than baseline. Why use AI to generate kernels for Apple devices? AI models execute on hardware via GPU kernels that define each oper

Topics: float self tensor torch uint

Shop Amazon

Important machine learning equations

news.ycombinator.com Unknown 2025-10-24 18:38:44

Motivation Machine learning (ML) is a powerful field driven by mathematics. Whether you’re building models, optimizing algorithms, or simply trying to understand how ML works under the hood, mastering the core equations is essential. This blog post is designed to be your go-to resource, covering the most critical and “mind-breaking” ML equations—enough to grasp most of the core math behind ML. Each section includes theoretical insights, the equations themselves, and practical implementations in

Topics: array np practical probability torch

Shop Amazon

The Most Important Machine Learning Equations: A Comprehensive Guide

news.ycombinator.com Unknown 2025-10-25 09:38:44

Motivation Machine learning (ML) is a powerful field driven by mathematics. Whether you’re building models, optimizing algorithms, or simply trying to understand how ML works under the hood, mastering the core equations is essential. This blog post is designed to be your go-to resource, covering the most critical and “mind-breaking” ML equations—enough to grasp most of the core math behind ML. Each section includes theoretical insights, the equations themselves, and practical implementations in

Topics: array np practical probability torch

Shop Amazon

The Annotated Transformer (2022)

news.ycombinator.com Unknown 2025-10-28 04:58:13

The Annotated Transformer v2022: Austin Huang, Suraj Subramanian, Jonathan Sum, Khalid Almubarak, and Stella Biderman. Original: Sasha Rush. The Transformer has been on a lot of people’s minds over the last year five years. This post presents an annotated version of the paper in the form of a line-by-line implementation. It reorders and deletes some sections from the original paper and adds comments throughout. This document itself is a working notebook, and should be a completely usable impl

Topics: def model return self torch

Shop Amazon

The Annotated Transformer

news.ycombinator.com Unknown 2025-10-28 09:58:13

The Annotated Transformer v2022: Austin Huang, Suraj Subramanian, Jonathan Sum, Khalid Almubarak, and Stella Biderman. Original: Sasha Rush. The Transformer has been on a lot of people’s minds over the last year five years. This post presents an annotated version of the paper in the form of a line-by-line implementation. It reorders and deletes some sections from the original paper and adds comments throughout. This document itself is a working notebook, and should be a completely usable impl

Topics: def model return self torch

Shop Amazon

Pfeilstorch

news.ycombinator.com Unknown 2025-11-13 14:07:49

Migrating stork which has been hit by an arrow The Rostocker Pfeilstorch, found in 1822, demonstrated that birds migrated rather than hibernating or changing form in winter. A Pfeilstorch (German for 'arrow stork', pronounced [ˈpfaɪ̯l.ˌʃtɔɐ̯ç]; plural Pfeilstörche, [-ˌʃtœɐ̯.çə]) is a white stork that is injured by an arrow or spear while wintering in Africa and returns to Europe with the projectile stuck in its body. As of 2003, about 25 Pfeilstörche have been documented in Germany.[1] The fi

Topics: arrows birds pfeilstorch stork white

Shop Amazon

DINOv3

news.ycombinator.com Unknown 2025-11-16 23:02:46

🆕 [2025-08-14] 🔥 DINOv3 backbones are now available in Hugging Face Hub and supported by the Hugging Face Transformers library DINOv3 🦖🦖🦖 Meta AI Research, FAIR Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt,

Topics: dataset dinov3 path torch url

Shop Amazon

Show HN: Learn LLMs LeetCode Style

news.ycombinator.com Unknown 2026-01-20 23:03:13

TorchLeet is broken into two sets of questions: Question Set: A collection of PyTorch practice problems, ranging from basic to hard, designed to enhance your skills in deep learning and PyTorch. LLM Set: A new set of questions focused on understanding and implementing Large Language Models (LLMs) from scratch, including attention mechanisms, embeddings, and more. Note Avoid using GPT. Try to solve these problems on your own. The goal is to learn and understand PyTorch concepts deeply. Table o

Topics: problems pytorch question questions set

Shop Amazon

AI leadership development platform Praxis Labs sells to Torch

techcrunch.com Dominic-Madori Davis 2026-01-21 16:00:00

Praxis Labs, a learning development platform, announced its acquisition on Thursday for an undisclosed amount by the leadership and coaching enterprise Torch. “As a small company with fewer than 20 people serving companies as large as Amazon, we knew we needed to build powerful partnerships, across product and go-to-market, to reach more companies,” co-founder and CEO of Praxis Labs, Elise Smith, told TechCrunch about the reason for the sale. She and her co-founder, Heather Shen, met Torch CEO

Topics: ai heather praxis torch ventures

Shop Amazon

Showh HN: Microjax – JAX in two classes and six functions

news.ycombinator.com Unknown 2026-02-03 00:41:55

Microjax: JAX in two classes and six functions or Read on Github (I recommend actually running the notebook, either on your own computer or Colab). This is inspired by Andrej Karpathy's Micrograd, a PyTorch-like library in about 150 lines of code. Despite PyTorch's popularity, I prefer the way JAX works because it a more functional style. This tutorial borrows heavily from Matthew J Johnson's great 2017 presentation on the predecessor to JAX, autograd: Video / Slides / Code. My main contribut

Topics: autograd code jax notebook pytorch

Shop Amazon

Showh HN: Microjax - Jax in two classes and six functions

news.ycombinator.com Unknown 2026-02-03 06:41:55

Microjax: JAX in two classes and six functions or Read on Github (I recommend actually running the notebook, either on your own computer or Colab). This is inspired by Andrej Karpathy's Micrograd, a PyTorch-like library in about 150 lines of code. Despite PyTorch's popularity, I prefer the way JAX works because it a more functional style. This tutorial borrows heavily from Matthew J Johnson's great 2017 presentation on the predecessor to JAX, autograd: Video / Slides / Code. My main contribut

Topics: autograd code jax notebook pytorch

Shop Amazon

Fault Tolerant Llama training – PyTorch blog

news.ycombinator.com Tristan Rice 2026-02-15 18:30:02

Collaborators: Less Wright, Howard Huang, Chien-Chin Huang, Crusoe: Martin Cala, Ethan Petersen tl;dr: we used torchft and torchtitan to train a model in a real-world environment with extreme synthetic failure rates to prove reliability and correctness of fault tolerant training Training loss across 1200 failures with no checkpoints. NOTE: Each small spike is a non-participating worker recovering which affects the metrics but not the model Introduction We want to demonstrate torchft in wo

Topics: group replica step torchft training

Shop Amazon

PyTorch Reshaping with None

news.ycombinator.com Unknown 2026-02-22 04:03:45

PyTorch Reshaping with None Currently I am learning attention mechanism from Dive into Deep Learning book. In the book I see following implementation in masked softmax: def sequence_mask (X, valid_len, value = - 1e6 ): """ X is 2D array (number_of_points, maxlen), valid_len is 1D array (number_of_points)""" max_len = X . size( 1 ) mask = torch . arange(max_len, dtype = torch . float32, device = X . device)[ None , :] < valid_len[:, None ] X[ ~ mask] = value return X In sequential data process

Topics: device mask max_len torch valid_len

Shop Amazon

DeepDive in everything of Llama3: revealing detailed insights and implementation

news.ycombinator.com Unknown 2025-11-13 02:57:13

[ View in English | 中文版文档点这里 ] This project is an enhanced version based on naklecha/llama3-from-scratch. It has been comprehensively improved and optimized on the basis of the original project, aiming to help everyone more easily understand and master the implementation principle and the detailed reasoning process of the Llama3 model. Thanks to the contributions of the original author :) The following are the core improvements of this project: Structural Optimization The presentation se

Topics: attention inf token tokens torch

Shop Amazon

Latest Tech News

Hydrogen-Powered Plasma Torch Decimates Plastic Waste in a Blink

Speeding up PyTorch inference on Apple devices with AI-generated Metal kernels

Speeding up PyTorch inference by 87% on Apple with AI-generated Metal kernels

Important machine learning equations

The Most Important Machine Learning Equations: A Comprehensive Guide

The Annotated Transformer (2022)

The Annotated Transformer

Pfeilstorch

DINOv3

Show HN: Learn LLMs LeetCode Style

AI leadership development platform Praxis Labs sells to Torch

Showh HN: Microjax – JAX in two classes and six functions

Showh HN: Microjax - Jax in two classes and six functions

Fault Tolerant Llama training – PyTorch blog

PyTorch Reshaping with None

DeepDive in everything of Llama3: revealing detailed insights and implementation

About GoKawiil

Privacy

Advertising

Latest Tech News

Trending Topics

Hot Now

Popular

Emerging

About GoKawiil

Privacy

Advertising