gpu programming
30 articles about gpu programming in AI news
Karpathy's 'Autoresearch' Tool Democratizes AI Research: One GPU, One Night, 100 Experiments
Andrej Karpathy has open-sourced 'autoresearch,' a tool that enables AI to autonomously improve its own training code. By writing simple prompts in Markdown, researchers can have AI agents run hundreds of experiments overnight on a single GPU, dramatically accelerating the research process.
NVFP4 GEMM on RTX Pro Blackwell: SM12x Breaks from B200 Programming Model
NVIDIA's SM12x architecture drops tcgen05.mma for mma.sync, breaking B200 kernel compatibility. SM8x kernels port easily; developers must maintain separate codebases.
Karpathy's Autonomous AI Researcher: Programming the Programmer in the Age of Agentic Science
Andrej Karpathy has open-sourced an autonomous AI research agent that can run ~100 experiments overnight without human supervision. The system turns research into a game with fixed-time trials, where prompt engineering replaces manual coding.
Jensen Huang Declares AI Has Democratized Programming Through 'Vibe Coding'
NVIDIA CEO Jensen Huang claims AI has eliminated the technology divide, enabling anyone to become a software programmer through 'vibe coding.' He cites examples of individuals creating million-dollar businesses using these new AI-powered development tools.
ByteDance's CUDA Agent: The AI System Outperforming Human Experts in GPU Code Generation
ByteDance has unveiled CUDA Agent, a large-scale reinforcement learning system that generates high-performance CUDA kernels. The system achieves state-of-the-art results, outperforming torch.compile by up to 100% and beating leading AI models like Claude Opus 4.5 and Gemini 3 Pro by approximately 40% on the most challenging tasks.
NVIDIA's cuQuantum-DGX OS Aims to Manage Hybrid Quantum-Classical Workflows
NVIDIA announced its AI software stack is evolving into an operating system for quantum computing, aiming to manage the complex workflow between quantum processors and classical GPUs. This targets a major integration bottleneck as quantum hardware scales.
InCoder-32B-Thinking Hits 81.3% on LiveCodeBench, Trained on Chip & Kernel Traces
InCoder-32B-Thinking, a 32B parameter model trained on execution traces from chip design, GPU kernels, and embedded systems, scores 81.3% on LiveCodeBench V5 and an 84% compile pass rate on CAD-Coder.
Karpathy's Autoresearch: Democratizing AI Experimentation with Minimalist Agentic Tools
Andrej Karpathy releases 'autoresearch,' a 630-line Python tool enabling AI agents to autonomously conduct machine learning experiments on single GPUs. This minimalist framework transforms how researchers approach iterative ML optimization.
Google's TensorFlow 2.21 Revolutionizes Edge AI with Unified LiteRT Framework
Google has launched TensorFlow 2.21, marking LiteRT's transition to a production-ready universal on-device inference framework. This major update delivers faster GPU performance, new NPU acceleration, and seamless PyTorch edge deployment, effectively replacing TensorFlow Lite for mobile and edge applications.
NVIDIA's SVG Benchmark Saturation Signals New Era in AI Graphics Performance
NVIDIA CEO Jensen Huang's presentation of the next RTX 6000 GPU series reveals that SVG benchmark performance has reached saturation, indicating a major milestone in AI-accelerated graphics rendering capabilities.
Cerebras' Strategic Partnership Yields Breakthrough AI Training Results
Cerebras Systems' partnership with Abu Dhabi's G42 has produced remarkable AI training benchmarks, achieving results 100x faster than traditional GPU clusters. The collaboration demonstrates the viability of wafer-scale computing for large language model development.
Rimnot, Yuantu Deploy 10K Robots in Server Factories by 2027
Rimnot partners Yuantu for 10K robots in server factories by 2027, achieving 30-minute adaptation at WAIC.
Soofi S 30B-A3B: German open model tops English, German benchmarks
German consortium releases Soofi S 30B-A3B, an open MoE model beating OLMo 3 and Apertus 70B on English and German benchmarks while activating only 3.2B of 31.6B parameters.
Jensen Huang Wants Zero Coding at NVIDIA — 'Purpose vs Task'
Jensen Huang wants zero coding by NVIDIA engineers, framing it as a task to minimize. The bet is AI-generated code will match human output for performance-critical software.
Ollama Now Runs Codex Locally: DeepSeek V4, Gemma 4, Qwen 3.6 Supported
Ollama integrates Codex support for DeepSeek V4, Gemma 4, Qwen 3.6, enabling free local code generation, challenging OpenAI's API model.
Pyptx: Write Nvidia PTX Kernels in Python for Hopper and Blackwell
Pyptx lets developers write and launch hand-tuned Nvidia PTX kernels directly from Python, supporting Hopper (sm_90a) and Blackwell (sm_100a). It provides explicit control over registers, shared memory, and advanced features like WGMMA and TMA, with dispatch through JAX, PyTorch eager, and torch.compile.
Use Claude Code to Automate Systematic Literature Reviews
Claude Code can automate systematic literature reviews: scrape papers, extract key themes, and generate structured summaries — all from the terminal.
Nvidia Invests $2B in Marvell for NVLink Fusion Interconnect
Nvidia is investing $2 billion in Marvell Technology to deepen their partnership on NVLink Fusion, a new interconnect architecture for scaling AI clusters beyond current limits.
Developer Achieves 395x RTFx on M5 Max with Fastest Parakeet v3 for Apple ANE
Developer @mweinbach has optimized the Parakeet v3 speech recognition model for Apple's Neural Engine, achieving a 395x real-time factor on an M5 Max chip. This represents a significant performance leap for on-device AI inference on Apple Silicon.
AI-Powered PS4 Emulator 'Spine' Runs Bloodborne Locally on PC
A developer has released Spine, a PS4 emulator that uses AI techniques to run Bloodborne fully on PC. This represents a major step forward in console emulation, previously considered years away.
Claude Code Builds Browser-Based 3D Flight Simulator in Weekend
A developer used Anthropic's Claude Code to build a complete 3D flight simulator that runs in a web browser over a weekend, demonstrating rapid AI-assisted game development.
Claude Code Runs 100% Locally on Mac via Native 200-Line API Server
A developer created a 200-line server that speaks Anthropic's API natively, allowing Claude Code to run entirely locally on M-series Macs at 65 tokens/second with no cloud dependency.
MLX-Benchmark Suite Launches as First Comprehensive LLM Eval for Apple Silicon
The MLX-Benchmark Suite has been released as the first comprehensive evaluation framework for Large Language Models running on Apple's MLX framework. It provides standardized metrics for models optimized for Apple Silicon hardware.
Qwen 3.6 Released: Free, Open-Weights Model for Local AI Coding
Alibaba's Qwen team released Qwen 3.6, an open-weights AI model for local deployment. This provides a free, private alternative to ID-verified models like Anthropic's Mythos and OpenAI's Codex.
NVIDIA Ising AI OS Cuts Quantum Calibration from Days to Hours
NVIDIA launched Ising, an open-source AI model family that acts as an OS for quantum computers. It uses a vision language model to automate calibration and a 3D neural network for error correction, reducing calibration from days to hours.
Claude Code's 'Shallow Thinking' Problem
Enterprise users report Claude Code sometimes skips deep analysis on complex tasks. Use specific prompting techniques and session management to ensure thorough reasoning.
NVIDIA CEO Jensen Huang Declares All Future Software Will Be Agentic
NVIDIA CEO Jensen Huang stated that all future software will be agentic, meaning every software company must transform into an agentic company. This vision positions AI agents as the fundamental architecture for future computing.
OpenAI Codex Now Translates C++, CUDA, and Python to Swift and Python for CoreML Model Conversion
OpenAI's Codex AI code generator is now being used to automatically rewrite C++, CUDA, and Python code into Swift and Python specifically for CoreML model conversion, a previously manual and error-prone process for Apple ecosystem deployment.
AI Engineer Henry Ndubuaku Releases Open-Source 'Maths, CS & AI Compendium' Textbook
AI engineer Henry Ndubuaku has published a free, open-source textbook compiling mathematics, computer science, and AI concepts. The resource emphasizes intuitive understanding over notation and has reportedly helped users land roles at DeepMind, OpenAI, and Nvidia.
Open-Source 'Manus Alternative' Emerges: Fully Local AI Agent with Web Browsing, Code Execution, and Voice Input
An open-source project has been released that replicates core features of AI agent platforms like Manus—autonomous web browsing, multi-language code execution, and voice input—while running entirely locally on user hardware with no external API dependencies.