Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
1.
Understanding FlashAttention Pt 1: Personal Notes (news.ycombinator.com)
2.
China-modified Nvidia RTX 5090 with massive 96GB of memory appears on Alibaba for less than $4,000 — 3x more VRAM at 65% the cost of the original (tomshardware.com)
3.
Thelio Mira AI Linux Workstation: 192 GB GPU Memory (news.ycombinator.com)
4.
What happens when a GPU writes memory (news.ycombinator.com)
5.
What happens when a GPU reads memory (news.ycombinator.com)
6.
Attention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization Guide (news.ycombinator.com)
7.
My first impressions on ROCm and Strix Halo (news.ycombinator.com)
8.
Nvidia says it can shrink LLM memory 20x without changing model weights (venturebeat.com)
9.
How to Spot (and Fix) 5 Common Performance Bottlenecks in Pandas Workflows (news.ycombinator.com)
10.
Unlocking Real-Time Supply Chain Analytics with GPU Technology: Q&A with Meher Siddhartha Errabolu (computer.org)
11.
GPUHammer: Rowhammer attacks on GPU memories are practical (news.ycombinator.com)
12.
NVIDIA shares guidance to defend GDDR6 GPUs against Rowhammer attacks (bleepingcomputer.com)
13.
NVIDIA's RTX 5050 arrives early in laptops from Acer, MSI and more (engadget.com)
14.
AMD's Pre-Zen Interconnect: Testing Trinity's Northbridge (news.ycombinator.com)
Today's top topics: google gemini openai tilly norwood piers morgan flock safety license plate readers surveillance technology voluntary severance ai safety
View all today's topics →