Topics
Results for “gpus”
112 results
- Claude Mythos slashed software work to onboard AMD GPUs to around three days — Hacker News · Seen · 43 points
- Chinese frontier AI models carry the fingerprint of export-controlled GPUs — Hacker News · Seen · 450 points
- speridlabs/idol — Hugging Face Models · Seen
- e-means: outperforming k-means (in one-tenth the epochs) — Hugging Face Papers · Seen · 17 points
- Flide: Accelerating Decision Inference with Exact State Forking — Hugging Face Papers · Seen · 37 points
- NVIDIA Announces Rubin HPC — A New GPU to Accelerate Agents for Science, Engineering and Analytics — NVIDIA Blog · Seen
- CUDA at 20: How the Platform Transformed Scientific Computing — NVIDIA Blog · Seen
- NVIDIA CUDA-X Libraries Give Agents the Tools to Accelerate Scientific Discovery — NVIDIA Blog · Seen
- NVIDIA Vera Rubin NVL72 Leads Agentic Inference Performance on MLPerf Endpoints v1.0 — NVIDIA Developer Blog · Seen
- Run GPU-Powered Black Hole Interferometry with NVIDIA cuPhoton — NVIDIA Developer Blog · Seen
- Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot — AWS Machine Learning Blog · Seen
- Write your own kernel optimiser — Hacker News · Seen · 41 points
- Six Serving Engines, One 8 GB GPU: Gemma 4 E2B on an RTX 3050 — DEV Community · Seen
- Nvidia Allegedly Engineered Scarcity by Funding AI Startups to Buy Its GPUs — Hacker News · Seen · 1,085 points
- Jensen Huang allegedly manufactured the GPU shortage — Hacker News · Seen · 46 points
- GPU says 35% busy. Busy doing what? — Hacker News · Seen · 5 points
- Smuggling of 1.5M AI GPUs could be the cause of Huang's departure — Hacker News · Seen · 54 points
- Nvidia deliberately kept GPU prices high through circular financing deals — Hacker News · Seen · 410 points
- Extending LLDB to Debug Applications That Span CPUs and GPUs — Hacker News · Seen · 33 points
- Validating GPU Platforms with Runtime AI Inventory via the NVIDIA DSX AI Factory — NVIDIA Developer Blog · Seen
- CAFIN: CUDA-accelerated Adaptive Fisher Information Matrix Network Optimization via GPU-Native Kernel Fusion — arXiv AI Papers · Seen
- One Word, Two GPUs: Why Gemma 4 Answers the Same Question Differently on a Laptop and a Tesla T4 — DEV Community · Seen
- Manage Kubernetes Clusters for GPU Infrastructure with NVIDIA Kubernetes Engine — NVIDIA Developer Blog · Seen
- Start and Restore GPU Workloads in Seconds with NVIDIA Snapshot — NVIDIA Developer Blog · Seen
- Agent Substrate: Advancing Kubernetes for Agents at Scale — NVIDIA Developer Blog · Seen
- e-means: 10x faster k-means at equal loss — 2 sources · Seen · 3 points
- ggml-org/llama.cpp — GitHub Trending · Seen
- Using voltage glitching to unleash the A100 in my mining card — 2 sources · Seen · 53 points
- Washing dishes at Denny's to rockstar of AI, the rise and fall of Jensen Huang — Hacker News · Seen · 14 points
- ExecuTorch WebGPU: PyTorch Models on the GPU, in the Browser — Hacker News · Seen · 9 points
- Google Summer of Code 2026 results — Lobsters · Seen · 19 points
- Show HN: DeepSeek-Coder-V2-Lite Under 5GB: 65 TPS 100% In-VRAM on 6GB GPU — Hacker News · Seen · 3 points
- NVIDIA Dynamo Recipes Bring Korea’s Leading Open Models to Production — NVIDIA Blog · Seen
- Compress any LLM 3x in one click, near-lossless, in under 50 MB RAM — Hacker News · Seen · 21 points
- A primer on GPUs and kernel optimization — Hacker News · Seen · 187 points
- Show HN: Daily GPU Rental Prices Across AWS, Azure, RunPod and Vast.ai — Hacker News · Seen · 11 points
- Show HN: JavaScript web apps with WASM layout and GPU rendering in 280 KB — Hacker News · Seen · 45 points
- Speed Up Image Generation with FLUX 3 Image Klein on NVIDIA Blackwell GPUs — NVIDIA Developer Blog · Seen
- Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU — Hacker News · Seen · 470 points
- SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints — AWS Machine Learning Blog · Seen
- Six GPUs on One X16 Slot: R9700s and RTX 3090s Behind a PCIe Switch — Hacker News · Seen · 5 points
- dsx-ai-factory/nvke — 2 sources · Seen
- Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU — Hacker News · Seen · 20 points
- Configure, Certify, and Operate Kubernetes GPU Clusters with NVIDIA DSX OS — NVIDIA Developer Blog · Seen
- More Performance From Every Byte: How Full-Stack Codesign Solves AI’s Memory Challenge — NVIDIA Blog · Seen
- Rune: A native GPU-rendered Rust UI framework for macOS, Windows, Linux and web — Hacker News · Seen · 177 points
- Good Luck Getting a Cheap GPU. AMD Is a 'Data Center First Company,' CEO Says — Hacker News · Seen · 18 points
- How NVIDIA Uses AI Agents to Streamline AI Factory Operations — NVIDIA Developer Blog · Seen
- NVIDIA CUDA 13.5 Brings NVIDIA Vera Rubin GA Support — NVIDIA Developer Blog · Seen
- GPU-Accelerated Weight Teleportation — Hacker News · Seen · 10 points
- Lowvram: A CLI tool to run large AI models in low VRAM GPUs — Hacker News · Seen · 3 points
- MoE Offloading Isn’t Always Faster: I Tested 5 Models on a 16GB GPU — DEV Community · Seen
- Diagnose Distributed AI Workload Failures with NVIDIA Attribution — NVIDIA Developer Blog · Seen
- Making Kubernetes AI-Ready for NVIDIA Vera Rubin on Day One — NVIDIA Developer Blog · Seen
- RTX 5090 Street Prices Top $9k as Nvidia GPU Costs Climb — Hacker News · Seen · 68 points
- JustVugg/colibri — GitHub Trending · Seen
- WiCi: Connecting GPUs over WiFi — Hacker News · Seen · 15 points
- FlashML-org/FreeToken — GitHub Trending · Seen
- Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs — DEV Community · Seen
- How to Check and Configure NVIDIA GPUDirect Storage for Your Platform — NVIDIA Developer Blog · Seen