Running Kimi K3 on MI355X at Better Performance per Dollar Than B300(wafer.ai)

192 points by ilreb 2 months ago | 94 comments

AMD MI300x GPUs with GEMM tuning improves throughput and latency by up to 7.2x(nscale.com)

60 points by latchkey 2 years ago | 43 comments

AMD Ryzen AI 9 HX 370 12-Core APU Is Faster Than M3 Max(wccftech.com)

18 points by doener 2 years ago | 3 comments

Cerebras Launches the Fastest AI Inference(cerebras.ai)

57 points by srameshc 2 years ago | 2 comments

Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs(baseten.co)

215 points by philipkiely 1 year ago | 142 comments

Summing ASCII encoded integers on Haswell at almost the speed of memcpy(blog.mattstuchlik.com)

114 points by iliekcomputers 2 years ago | 34 comments

GPUs Go Brrr(hazyresearch.stanford.edu)

1056 points by nmstoker 2 years ago | 243 comments

Stanford Hazy Research blog post on what GPU hardware wants for efficient AI kernels, introducing the ThunderKittens CUDA kernel library.

We were wrong about GPUs(fly.io)

834 points by mxstbr 1 year ago | 529 comments

Fly.io blog post reflecting on how the company's bet on offering GPU machines to developers did not pan out as expected.

Ollama now supports AMD graphics cards(ollama.com)

578 points by tosh 2 years ago | 194 comments

Ollama blog post from March 14, 2024 announcing preview support for running models on AMD graphics cards.

Nvidia buys $5B in Intel(tomshardware.com)

935 points by stycznik 1 year ago | 569 comments

Tom's Hardware report on Nvidia buying $5 billion in Intel stock and the two jointly developing x86 RTX SoCs for PCs and custom data center x86 CPUs.

DRAM pricing is killing the hobbyist SBC market(jeffgeerling.com)

576 points by ingve 6 months ago | 504 comments

Jeff Geerling blog post on Raspberry Pi price increases driven by DRAM costs, with an embedded video on the state of the hobbyist SBC market.

Nvidia, CoreWeave, and Nebius: Inside the Circular Financing of the GPU Boom(io-fund.com)

354 points by adletbalzhanov 3 months ago | 153 comments

An I/O Fund blog post analyzing the circular financing relationships among Nvidia, CoreWeave, and Nebius in the AI GPU boom.