Tagged: AMD

AMD's MI250 doubles A100 speed on Hugging Face models with zero code changes

Aug 20

AMD buys AI chip startup Taalas to etch models directly into silicon, hits 17,000 tokens/sec

Aug 10

AMD buys Taalas to bake Llama 3.1 into silicon at 16,000 tokens per second

Aug 7

AMD buys Taalas to bake AI models into silicon, hitting 17,000 tokens/sec

Aug 6

AMD's data center revenue hits $6.7B, doubling in a year as gaming plunges 31%

Aug 4

AMD ships a 16B-param MoE model trained entirely on its own GPUs, but the license is research-only

Aug 1

AMD and Cerebras team up to take on Nvidia's Groq LPUs together

Jul 23

AMD's Helios rack beats Nvidia's Vera Rubin on key metrics, ships this year

Jul 23

AMD bets $5B on Anthropic to build a 2-gigawatt AI empire by 2027

Jul 23

Anthropic inks $5B AMD deal to power Claude with 2 gigawatts of GPUs by 2027

Jul 22

AMD bets $5B on Anthropic with massive 2-gigawatt GPU deal for 2027

Jul 22

AMD's Helios chips land Microsoft, and Anthropic may be next

Jul 20

AMD inks 6-gigawatt GPU deal with OpenAI — and a 160M share kicker

Jul 12

AMD attacks the rack with Helios: bigger, faster than Nvidia's Vera Rubin on paper

May 5

AMD's new Helios rack out-specs Nvidia's Vera Rubin on paper, targets CUDA with ROCm

May 5

AMD's Helios racks beat Nvidia's Vera Rubin on paper — but paper's cheap

May 5

AMD's Helios racks target Nvidia's Vera Rubin with bigger specs on paper

May 5

Anthropic's Opus 5 cuts price in half, ditches mandatory data retention

Apr 29

Anthropic's Opus 5 ships at half price, drops mandatory data retention

Apr 28

Hugging Face Now Lets You Build and Share AMD ROCm Kernels Without the Toolchain Headaches

Nov 17

AMD drops $10K prize for the best SO-101 robot hack in Tokyo and Paris

Nov 13

Custom CUDA kernels juice Llama 3.1 405B on AMD MI300X, skipping Nvidia lock-in

Jul 9

AMD's 192-core Turin chip doubles Llama 3 speed, no GPU required

Oct 10