Loading...
Loading...
Browse all stories on DeepNewz
VisitWhich company's AI inference solution will be fastest by mid-2025?
Nvidia • 25%
Cerebras • 25%
Google • 25%
Other • 25%
Benchmark reports from reputable sources such as MLPerf or independent testing labs
Cerebras Challenges Nvidia with Fastest AI Inference Service
Aug 27, 2024, 04:05 PM
Cerebras Systems has launched what it claims to be the world's fastest AI inference service, marking a significant challenge to Nvidia's dominance in the AI computing sector. The new service, powered by Cerebras' custom wafer-scale AI accelerator chips, offers AI developers access to high-speed applications at a lower cost. Cerebras has set a new record for AI inference speed, serving Llama 3.1 8B at 1,850 output tokens per second and 70B at 446 output tokens per second. This move is part of a broader trend where several chipmakers are attempting to break Nvidia's stronghold in the AI market.
View original story
Cerebras • 25%
Nvidia • 25%
Groq • 25%
Other • 25%
Amazon • 25%
Nvidia • 25%
Microsoft • 25%
Alphabet • 25%
OpenAI • 25%
Google • 25%
Meta • 25%
Other • 25%
AMD • 25%
Intel • 25%
NVIDIA • 25%
Other • 25%
OpenAI • 25%
Google • 25%
Amazon • 25%
Microsoft • 25%
xAI • 25%
Google DeepMind • 25%
OpenAI • 25%
Nvidia • 25%
Nvidia • 25%
OpenAI • 25%
Anthropic • 25%
Other • 25%
Cerebras • 25%
Nvidia • 25%
Groq • 25%
Other • 25%
NVIDIA • 25%
Apple • 25%
Qualcomm • 25%
Google • 25%
NVIDIA • 25%
Intel • 25%
AMD • 25%
Other • 25%
Nvidia maintains lead • 25%
Amazon surpasses Nvidia • 25%
Amazon matches Nvidia • 25%
Other company leads • 25%
Google • 25%
OpenAI • 25%
Microsoft • 25%
Other • 25%
No • 50%
Yes • 50%
Cerebras • 25%
Other • 25%
Nvidia • 25%
Intel • 25%