Login
TPUs vs. GPUs and why Google is positioned to win AI race in the long term
(uncoveralpha.com) by vegasbrianc | view | 320 comments
AMD GPUs Go Brrr
(hazyresearch.stanford.edu) by vinhnx | view | 92 comments
OrthoRoute – GPU-accelerated autorouting for KiCad
(bbenchoff.github.io) by wanderingjew | view | 29 comments
Nvidia is gearing up to sell servers instead of just GPUs and components
(tomshardware.com) by giuliomagnifico | view | 77 comments
Simulating a Planet on the GPU: Part 1 (2022)
(patrickcelentano.com) by Doches | view | 19 comments
Optimizing Datalog for the GPU
(danglingpointers.substack.com) by blakepelton | view | 26 comments
PayPal bans Linux users with a GPU name containing the string "Apple M1"
(vt.social) by robin_reala | view | 43 comments
Ilya Sutskever, Yann LeCun and the End of “Just Add GPUs”
(abzglobal.net) by birdculture | view | 131 comments
Show HN: a Rust ray tracer that runs on any GPU – even in the browser
(github.com) by tchauffi | view | 29 comments
We built a cloud GPU notebook that boots in seconds
(modal.com) by birdculture | view | 34 comments
CPUs and GPUs to Become More Expensive After TSMC Price Hike in 2026
(guru3d.com) by elorant | view | 80 comments
Racing karts on a Rust GPU kernel driver
(collabora.com) by mfilion | view | 14 comments
Strix Halo's Memory Subsystem: Tackling iGPU Challenges
(chipsandcheese.com) by PaulHoule | view | 35 comments
Client-side GPU load balancing with Redis and Lua
(galileo.ai) by lneiman | view | 11 comments
WebGPU is now supported in major browsers
(web.dev) by astlouis44 | view | 5 comments
Raycore: GPU accelerated and modular ray intersections
(makie.org) by simondanisch | view | 3 comments
GT – Experimental multiplexing tensor framework for distributed GPU computing
(github.com) by brrrrrm | view | 1 comments
Sysgpu – Experimental descendant of WebGPU written in Zig
(github.com) by coffeeaddict1 | view | 4 comments
Using AMD GPUs on Raspberry Pi Without Recompiling Linux
(jeffgeerling.com) by furkansahin | view | 2 comments
Show HN: GPULlama3.java Llama Compilied to PTX/OpenCL Now Integrated in Quarkus
by mikepapadim | view | 6 comments
Show HN: RunMat – runtime with auto CPU/GPU routing for dense math
(github.com) by nallana | view | 4 comments
Text rendering and effects using GPU-computed distances
(blog.pkh.me) by PaulHoule | view | 0 comments
Show HN: OSS implementation of Test Time Diffusion that runs on a 24gb GPU
(github.com) by eamag | view | 0 comments
Apex GPU: Run CUDA Apps on AMD GPUs Without Recompilation
(github.com) by ArchitectAI | view | 6 comments
I just trained a physics-based earthquake forecasting model on a $1000 GPU
by ArchitectAI | view | 7 comments
Mobile GPUs and Tile-Based Rendering
(hyeondg.org) by jakogut | view | 2 comments
RIP Windows: Linux GPU Gaming Benchmarks on Bazzite [video]
(youtube.com) by doener | view | 0 comments
Show HN: A real-time 4D fractal explorer in the browser using WebGPU
(bryanjj.github.io) by bryan0 | view | 5 comments
Linus Torvalds – Talks about AI Hype, GPU Power, and Linux's Future
(youtube.com) by belter | view | 0 comments
Show HN: Zephyr3D – TypeScript WebGPU/WebGL 3D engine with an in‑browser editor
(zephyr3d.org) by gavinyork | view | 1 comments
GPU depreciation could be the next big crisis for hyperscalers
(tomshardware.com) by gmays | view | 4 comments
AMD GPUs Go Brrr
(hazyresearch.stanford.edu) by todsacerdoti | view | 0 comments
The AI Mega Mesh: How to Connect 30 GPU Cloud Providers
(netbird.io) by devildriver89 | view | 0 comments
Nvidia reportedly no longer supplying VRAM to GPU partners due to memory crunch
(tomshardware.com) by lysp | view | 1 comments
Microsoft CEO: Not enough electricity for all AI GPUs in inventory
(tomshardware.com) by speckx | view | 1 comments
Nvidia rumored to stop bundling memory with GPUs, squeezing smaller partners
(videocardz.com) by davikr | view | 0 comments
ParallelKittens: Simple and Fast Multi-GPU AI Kernels
(hazyresearch.stanford.edu) by pella | view | 0 comments
Show HN: Serve 100 Large AI models on a single GPU with low impact to TTFT
(github.com) by leonheuler | view | 1 comments
Show HN: Train a language model in the browser with WebGPU
(sequence.toys) by vvin | view | 1 comments
New Chinese optical quantum chip allegedly 1,000x faster than Nvidia GPUs for AI
(tomshardware.com) by openmaze | view | 0 comments
New Chinese optical quantum chip allegedly 1,000x faster than Nvidia GPUs
(tomshardware.com) by thunderbong | view | 2 comments
All Intel GPUs Run on Raspberry Pi and RISC-V
(jeffgeerling.com) by mikece | view | 0 comments
Nvidia says its GPUs are a 'generation ahead' of Google's AI chips
(cnbc.com) by kjhughes | view | 3 comments
GPU depreciation could be the next big crisis coming for AI hyperscalers
(tomshardware.com) by giuliomagnifico | view | 0 comments
Show HN: LLMKube – Kubernetes for Local LLMs with GPU Acceleration
(github.com) by defilan | view | 0 comments
Show HN: Unrestricted Windows automation MCP with 9.68x GPU amplification
(github.com) by Opus_Warrior | view | 0 comments
Valve engineer keeps decade-old Radeon GPUs alive on Linux
(videocardz.com) by danboarder | view | 0 comments
TornadoVM v2.0.0 release with lots of improvements for Java on GPUs
(github.com) by pjmlp | view | 0 comments
Inside VOLT: Designing an Open-Source GPU Compiler
(arxiv.org) by matt_d | view | 0 comments
Show HN: modal-cuda – CLI to run CUDA .cu programs on Modal GPUs
(github.com) by Sai_Praneeth | view | 0 comments