We Got Claude to Build CUDA Kernels and teach open models!

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

We Got Claude to Fine-Tune an Open Source LLM

Custom Kernels for All from Codex and Claude

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels

arXiv:2607. 24762v1 Announce Type: new Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolution, and normalization.

Bringing open AI models to the frontier

Why we're building Mistral AI.

How To Build Your Own LLM Runtime From Scratch

If you have ever wanted to actually build an LLM inference runtime yourself — pack your own weights, own every barrier, capture your own CUDA graphs — this is what that journey looks like on an H100. A step-by-step tour of a small runtime called annotated-llm-runtime, and the three bugs that produced most of the annotations.

Announcing the OpenAI Learning Accelerator

Welcome GPT OSS, the new open-source model family from OpenAI!

OpenAI Fellows Summer 2018: Final projects

Our first cohort of OpenAI Fellows has concluded, with each Fellow going from a machine learning beginner to core OpenAI contributor in the course of a 6-month apprenticeship.

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

arXiv:2602. 11715v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation.

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

arXiv:2512. 02551v3 Announce Type: replace-cross Abstract: In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels.

Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

arXiv:2604. 23466v2 Announce Type: replace Abstract: NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs.