Jalapeño is a custom inference chip from OpenAI that delivers faster, more power-efficient AI inference, with higher throughput and lower latency for modern models.

Recommended

Announcing the initial People-First AI Fund granteesOpenai Operation "Doppelganger": Russian influence activity targeting UkraineOpenai Everyday work with ChatGPT WorkOpenai Romance scams: AI-enabled romance scam workflowsOpenai Will Hurd joins OpenAI’s board of directorsOpenai Statement from the OpenAI Board of Directors on the Nonprofit Commission ReportOpenai Video: Building a Live Transcription Badge With Deepgram - Deepgram Blog ⚡️Video: Building a Live Transcription Badge With Deepgram - Deepgram Blog ⚡️Deepgram Who Explains the Most? An Analysis of Educational YouTubers - Deepgram Blog ⚡️Who Explains the Most? An Analysis of Educational YouTubers - Deepgram Blog ⚡️Deepgram The Simplest Possible Neural Network, Explained - Deepgram Blog ⚡️The Simplest Possible Neural Network, Explained - Deepgram Blog ⚡️Deepgram Calling Your Video Game With Your Phone: Part 1Calling Your Video Game With Your Phone: Part 1Deepgram Automate Audio Transcription with Zapier + DeepgramAutomate Audio Transcription with Zapier + DeepgramDeepgram The Proven Redis PerformanceThe Proven Redis PerformanceRedis Redis Labs’ Customers Award Accolades!Redis Labs’ Customers Award Accolades!Redis How Redis is Used in Practice | RedisHow Redis is Used in Practice | RedisRedis Data Ingestion: 6 Ways to Speed Up Your ApplicationData Ingestion: 6 Ways to Speed Up Your ApplicationRedis Puppet’s New Mission: Automating Cloud Native InfrastructurePuppet’s New Mission: Automating Cloud Native InfrastructureThenewstack DevSecOps: Why Security Shouldn’t be Sacrificed for SpeedDevSecOps: Why Security Shouldn’t be Sacrificed for SpeedThenewstack Go 2017 Survey Results - The Go Programming LanguageGo 2017 Survey Results - The Go Programming LanguageGo Go 2018 Survey Results - The Go Programming LanguageGo 2018 Survey Results - The Go Programming LanguageGo How to serve trillions of tokens for trillion-parameter coding agentsHow to serve trillions of tokens for trillion-parameter coding agentsModal