RDMA networking + MPI for consumer GPU clusters — no managed switch required
TPUs vs. GPUs and why Google is positioned to win AI race in the long term | Hacker News
To quote The Next Platform: "An Ironwood cluster linked with Google’s absolutely unique optical circuit switch interconnect can bring to bear 9,216 Ironwood TPUs with a combined 1.77 PB of HBM memory... This makes a rackscale Nvidia system based on 144 “Blackwell” GPU chiplets with an aggregate of 20.7 TB of HBM memory look like a joke."
Pricing | Runpod
GPU cloud computing at up to 80% less than hyperscalers. Explore pricing for on-demand Pods, Serverless, Clusters, and Network Storage.
RightNow AI - YC-Backed GPU Research Lab
YC-backed GPU research lab building the RightNow CUDA editor, RunInfra inference infra, Forge kernels, and publishing AutoMegaKernel and related papers on arXiv.
Mesh LLM: distributed AI computing on iroh
How Mesh LLM pools existing GPU resources across machines into a single OpenAI-compatible API, built on iroh.
GPU Pricing — Live Platform Rates | Vast.ai
Live GPU pricing on Vast.ai. Prices set by supply and demand across 40+ data centers. On-demand, interruptible, or reserved — find the right GPU at the right price.
Brandon on Twitter / X
I think we might need a new TensorFlow.js for the modern WebGPU era. The best starting point for this library is, ironically, TensorFlow.js with WebGPU backend. But, like three.js, there are indications that not designing them from the ground up around WebGPU can lead to…— Brandon (@brandon_xyzw) December 6, 2025
Ash Hart on Twitter / X
MLX <RDMA> CUDA Update.Apple's Thunderbolt RDMA protocol is mapped with the XDomain header, the 0xFA57 UUID, login/logout, and the NHI descriptor bits, all confirmed against the AppleThunderboltNHI kext. Cloud models said no. A local model (DeepSeek) + a kext disassembly said… pic.twitter.com/jRmDHNC8YQ— Ash Hart (@ashxhart) August 16, 2026
Iwo Plaza – Your GPU is a JavaScript runtime* (TypeGPU deep-dive)
NVIDIA Levels Up Local AI Agents Across RTX PCs and DGX Spark
Announced at GTC Taipei at COMPUTEX, NVIDIA OpenShell brings secure agents to Windows with 2x inference performance on llama.cpp — plus, Adobe rebuilds its apps with performance and memory enhancements, and Blender adds NVIDIA DLSS 4.5 Ray Reconstruction for NVIDIA RTX Spark.
Bringing Edge AI to the Raspberry Pi GPU | Igalia
Igalia is an open source consulting firm specialised in the development of innovative projects and solutions. Our engineers have expertise in a wide range of technological areas, including browsers and client-side web technologies, graphics pipeline, compilers and virtual machines. We have the most WPE, WebKit, Chromium/Blink and Firefox expertise found in the consulting business, including many reviewers and committers. Igalia designs, develops, customises and optimises GNU/Linux-based solutions for companies across the globe. Our work and contributions are present in many projects such as GStreamer, Mesa 3D, WebKit, Chromium, etc.
Nvidia wants your home network to work like a mini data center for local AI
Nvidia's PAIR (Personal AI Router) automatically spreads local AI requests across all available devices on a home network, cutting wait times for parallel agent tasks.
Run Ollama with NVIDIA GPU in Proxmox VMs and LXC containers
Learn how to run Ollama with an NVIDIA GPU in Proxmox for an enhanced AI experience in your home lab and great chat performance
