shipfeedAI news, curated daily

19:32:43 CET
24 JUN19:32:43shipfeed
pull to refreshlast sync
Just in — 30 new
§ models · storyline

OpenAI and Broadcom unveil Jalapeño, LLM inference chip

OpenAI and Broadcom unveil Jalapeño, an LLM-optimised inference chip developed in nine months that delivers improved performance per watt over current accelerators.

today · · primary fetch3 sourcesupdated today ·

OpenAI: OpenAI and Broadcom unveil Jalapeño, an LLM-optimized inference chip developed from design to manufacturing tape-out in nine months, aided by OpenAI's models — Loading...

- Early testing shows that the first-generation accelerator will deliver performance per watt substantially better than current state-of-the-art

read full article on openai.com
§ sources3 publications · timeline below
  1. openai.comOpenAI and Broadcom unveil Jalapeño, an LLM-optimized inference chip developed from design to manufacturing tape-out in nine months, aided by OpenAI's models (OpenAI)primary
  2. theverge.comOpenAI reveals its first AI processor: Jalapeño
  3. the-decoder.comOpenAI and Broadcom unveil "Jalapeño," a custom chip built for LLM inference

§ how this story moved

  1. primaryOpenAI publishes the launch post.
  2. The Decoder picks up coverage.
  3. The Verge — AI picks up coverage.