"The new push into inference comes as Huang said Nvidia projects massive demand. The company expects at least $1 trillion in demand for its Blackwell and Rubin AI systems through 2027 - up from about $500 billion in projected demand through 2026, he said."
"The AI chip giant announced the new Nvidia Groq 3 LPX, which Huang said can speed up inference workloads by up to 35 times. It integrates technology from AI chip startup Groq and pairs it with Nvidia's Vera Rubin architecture."
"Now, a growing number of Nvidia competitors - from hyperscalers to chip startups - are developing specialized systems that are cheaper and more efficient for the repetitive and cost-sensitive work of inference."
Nvidia CEO Jensen Huang introduced the Groq 3 LPX inference system at GTC, marking the company's strategic response to inference becoming AI's next competitive frontier. The system integrates technology from AI chip startup Groq, following Nvidia's $20 billion deal with the company in December. The Groq 3 LPX can accelerate inference workloads by up to 35 times and combines Groq's technology with Nvidia's Vera Rubin architecture. Samsung manufactures the chip, with shipments expected in the second half of 2024. Huang emphasized the inflection point of inference has arrived, noting Nvidia projects $1 trillion in demand for its Blackwell and Rubin systems through 2027, up from $500 billion projected through 2026.
#ai-inference-systems #nvidia-groq-partnership #gpu-technology #ai-chip-competition #machine-learning-acceleration
Read at Business Insider
Unable to calculate read time
Collection
[
|
...
]