Gpu Computing RSS Feeds

Directory0 gpu computing feeds · 17 articlesShow all languages →

Latest

Gpu Computing articles

Rotary GPU: Enabling Large Mixture-of-Experts Models on Consumer Laptop GPUs with Limited Memory

This paper presents Rotary GPU, an exploratory approach to running large Mixture-of-Experts (MoE) language models on consumer-grade hardware with limited GPU memory. The authors conducted a public validation using a Qwen3.6-35B-A3B-class MoE model on a laptop with an RTX 4060 GPU

Insighttechnologymachine learningprogramming

arxiv.org·Hacker News: Front Page·1d ago·2 min read

Unsloth and NVIDIA Partner to Accelerate LLM Fine-Tuning by 20%

Newstechnologyprogramminggpu computing

Unsloth - Train and Run Models Locally24d ago

Systalyze's Utilyze Tool Reveals True GPU Compute Utilization in AI Workloads

Insighttechnologyprogramminggpu computing

systalyze.com1mo ago

Eyot: A Programming Language That Makes GPU Programming as Simple as Background Threads

Newstechnologyprogrammingsoftware development

cowleyforniastudios.com2mo ago

Virtualizing NVIDIA HGX B200 GPUs with Open-Source Software

This technical blog post details the process of virtualizing NVIDIA HGX B200 GPUs using open-source software. It covers hardware overview, Fabric Manager configuration for shared NVSwitch multitenancy mode, VFIO passthrough implementation, QEMU PCI topology fixes, and solutions f

technologyprogrammingvirtualization

ubicloud.com·Hacker News: Front Page·5mo ago·2 min read

Exploring GPU Debugging Tools and the Search for AMD GPU Debugger Solutions

The article discusses the author's exploration of GPU debugging tools, specifically focusing on the lack of comprehensive GPU debuggers compared to CPU debuggers. The author describes discovering rocgdb for AMD's ROCm environment and being inspired by blog posts from Marcell Kiss

Insighttechnologyprogrammingsoftware development

thegeeko.me·Hacker News: Front Page·5mo ago·37 min read

GPU-Optimized Datalog Evaluation: GPULOG System Analysis from ASPLOS'25 Paper

This article analyzes the ASPLOS'25 paper 'Optimizing Datalog for the GPU,' which presents GPULOG, a system that optimizes Datalog evaluation for GPU execution. The paper introduces techniques using hash-indexed sorted arrays to accelerate Datalog queries on GPUs, outperforming e

Insighttechnologyprogramminggpu computing

danglingpointers.substack.com·Hacker News: Front Page·6mo ago·4 min read

Cuq Framework: Formal Verification of Rust GPU Kernels Targeting PTX Architecture

Codetechnologyprogramminggpu computing

github.com7mo ago

NVIDIA DGX Spark Review: Compact Workstation for High-Performance AI Inference

Reviewtechnologyprogrammingai hardware

lmsys.org7mo ago

Implementing Cellular Automata with WebGPU Compute Shaders

technologyprogramminggpu computing

vectrx.substack.com7mo ago

RightNow AI Launches First GPU-Native Code Editor with CUDA Support

Producttechnologyprogrammingdeveloper tools

Product Hunt4mo ago

Mojo Programming Language Adds Apple Silicon GPU Support

Newstechnologyprogrammingdeveloper tools

forum.modular.com8mo ago

GPU Programming Project: Implementing Parallelizable RNNs with CUDA

technologyprogramminggpu computing

dhruvmsheth.github.io8mo ago

GPUPrefixSums: A portable collection of GPU prefix sum algorithms for CUDA, D3D12, Unity, and WGPU

GPUPrefixSums is an open-source GitHub project that implements a comprehensive collection of prefix sum algorithms for GPUs, supporting CUDA, D3D12, Unity, and WGPU. It aims to make state-of-the-art GPU prefix sum techniques portable across different compute shader environments.

Codetechnologyprogrammingopen source

github.com·Hacker News: Front Page·9mo ago·7 min read