TechCrunch · Startups · 2026-08-25
OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show
Tested on Semianalysis’s 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 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.
Read original on TechCrunch Get the app
Licensed summary · LicensedSummary
Related briefs
- Gamma acquires Accel-backed design startup Lica
- Apple rescues Hide My Email feature from the privacy scrap heap
- Apple debuts its ‘most powerful chip ever’ in M5 Ultra and M6
- Self-driving truck startup Gatik raises $200M following PepsiCo deal
- Apple’s latest Mac Mini runs on a new M6 chip, and starts at $899