Jalapeño measures 1.9x per watt against a GB200
A photograph of a chip sitting on a teal test board, and finally some numbers under it. OpenAI published Jalapeño's first measured results on 25 August, and the short version ...
Tag: inference
Ramp Router is free until January, with a year of retention
Your model bill went up again and nobody on the team can say which feature did it. That's the itch Ramp is scratching. On 19 August it opened Router, the ...
Cerebras stacks three wafers for 750 PFLOPS
Look at the spec table for two minutes and the story falls out on its own. Every number on the WSE-3 Turbo is exactly double the WSE-3: 125 petaflops becomes ...
Groq raised $350M and now sells Nvidia capacity
Groq spent years selling one idea, that Nvidia was the wrong shape for inference and a custom chip called an LPU was the right one. On 12 August it became ...
GPT-5.6 Sol Ultrafast hits 750 tokens a second, with no price
Cerebras published a bar chart with a 14x on it, and the bar beside it says 2.5x. That is the pitch for Ultrafast, the OpenAI API service tier previewed on ...
Etched raises $300M at $10.3B: where did Sohu go?
We went looking for the Sohu spec sheet, and it is not there any more. Etched raised 300 million dollars on July 23 at a 10.3 billion dollar valuation, led ...
Fireworks raised $1.5B, and a raise ships no code
You read our piece on Qwen 3.8, nodded at the open weights, then hit the same wall we always do. Great, now where do you actually run a near trillion-parameter ...
Meta’s Iris chip enters production in September
A leaked internal memo, not a keynote, is how we found out Meta has a new chip. On July 9 Reuters reported it: Iris, the latest in Meta's in-house MTIA ...
OpenAI’s first chip, Jalapeño, is built for inference
Sam Altman got handed a chip on a stage, and the AI hardware race picked up a new character. On June 24, OpenAI and Broadcom unveiled Jalapeño, OpenAI's first custom ...