Tested on SemiAnalysis’ InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the art.
OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show
By Chronicle Newsroom · · Source: TechCrunch
Tested on SemiAnalysis’ InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the art.
Related stories
Technology· 7m ago
Pacific Fusion’s next fusion machine could clear a key hurdle to commercial power
Fusion startup Pacific Fusion broke ground on a demonstration facility in New Mexico that it says will generate enough energy to power itself.
TechCrunch
Technology· 37m ago
Gamma acquires Accel-backed design startup Lica
Lica co-founders are going to work on Gamma's new research team.
TechCrunch
Technology· 51m ago
Apple rescues Hide My Email feature from the privacy scrap heap
Apple says it will no longer ditch using its icloud.com domain for hiding people's email addresses.
TechCrunch
More from Chronicle
- New 10p coin enters circulation - will you spot one?
- Kit Harington joins HBO's Harry Potter series as Gilderoy Lockhart
- Palmer shines as Chelsea secure narrow victory over Fulham
- Al-Hilal nearing deal to acquire Arsenal's Gabriel Martinelli
- Rogers & Palmer star but Sanchez struggles - Fulham v Chelsea player ratings
- Man City linked with Gakpo as transfer rumors swirl
- Zillow, Redfin Resolve FTC Dispute Over Rental Ad Practices
- England's World Cup Dream Dashed by Netherlands Stalemate
- Reserve Your Startup Exhibit Spot at TechCrunch Disrupt 2026
- Hodgkinson withdraws from Zurich Diamond League
- Alabama launches investigation into OpenAI’s hack of Hugging Face
- Manga-inspired theme park to be built near Paris