•1 min read•from TechCrunch
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.
Want to read more?
Check out the full article on the original site
Tagged with
#OpenAI
#Jalapeño
#inference
#scale
#benchmarks
#SemiAnalysis
#InferenceX
#tokens per user
#throughput
#kilowatt
#state-of-the-art
#AI
#performance
#machine learning
#deep learning
#model
#optimization
#efficiency
#compute