Cerebras Methods, a pioneer in high-performance AI compute, has launched a groundbreaking answer that’s set to revolutionize AI inference. On August 27, 2024, the corporate introduced the launch of Cerebras Inference, the quickest AI inference service on the planet. With efficiency metrics that dwarf these of conventional GPU-based techniques, Cerebras Inference delivers 20 occasions the pace at a fraction of the price, setting a brand new benchmark in AI computing.
Unprecedented Pace and Value Effectivity
Cerebras Inference is designed to ship distinctive efficiency throughout varied AI fashions, notably within the quickly evolving phase of giant language fashions (LLMs). As an example, it processes 1,800 tokens per second for the Llama 3.1 8B mannequin and 450 tokens per second for the Llama 3.1 70B mannequin. This efficiency is just not solely 20 occasions quicker than that of NVIDIA GPU-based options but additionally comes at a considerably decrease price. Cerebras provides this service beginning at simply 10 cents per million tokens for the Llama 3.1 8B mannequin and 60 cents per million tokens for the Llama 3.1 70B mannequin, representing a 100x enchancment in price-performance in comparison with current GPU-based choices.
Sustaining Accuracy Whereas Pushing the Boundaries of Pace
Probably the most spectacular elements of Cerebras Inference is its potential to take care of state-of-the-art accuracy whereas delivering unmatched pace. Not like different approaches that sacrifice precision for pace, Cerebras’ answer stays throughout the 16-bit area for the whole thing of the inference run. This ensures that the efficiency positive aspects don’t come on the expense of the standard of AI mannequin outputs, a vital issue for builders targeted on precision.
Micah Hill-Smith, Co-Founder and CEO of Synthetic Evaluation, highlighted the importance of this achievement: “Cerebras is delivering speeds an order of magnitude faster than GPU-based solutions for Meta’s Llama 3.1 8B and 70B AI models. We are measuring speeds above 1,800 output tokens per second on Llama 3.1 8B, and above 446 output tokens per second on Llama 3.1 70B – a new record in these benchmarks.”
The Rising Significance of AI Inference
AI inference is the fastest-growing phase of AI compute, accounting for roughly 40% of the whole AI {hardware} market. The arrival of high-speed AI inference, akin to that provided by Cerebras, is akin to the introduction of broadband web—unlocking new alternatives and heralding a brand new period for AI functions. With Cerebras Inference, builders can now construct next-generation AI functions that require complicated, real-time efficiency, akin to AI brokers and clever techniques.
Andrew Ng, Founding father of DeepLearning.AI, underscored the significance of pace in AI improvement: “DeepLearning.AI has multiple agentic workflows that require prompting an LLM repeatedly to get a result. Cerebras has built an impressively fast inference capability which will be very helpful to such workloads.”
Broad Trade Help and Strategic Partnerships
Cerebras has garnered sturdy help from {industry} leaders and has fashioned strategic partnerships to speed up the event of AI functions. Kim Branson, SVP of AI/ML at GlaxoSmithKline, an early Cerebras buyer, emphasised the transformative potential of this expertise: “Speed and scale change everything.”
Different corporations, akin to LiveKit, Perplexity, and Meter, have additionally expressed enthusiasm for the influence that Cerebras Inference may have on their operations. These corporations are leveraging the facility of Cerebras’ compute capabilities to create extra responsive, human-like AI experiences, enhance person interplay in engines like google, and improve community administration techniques.
Cerebras Inference: Tiers and Accessibility
Cerebras Inference is out there throughout three competitively priced tiers: Free, Developer, and Enterprise. The Free Tier offers free API entry with beneficiant utilization limits, making it accessible to a broad vary of customers. The Developer Tier provides a versatile, serverless deployment choice, with Llama 3.1 fashions priced at 10 cents and 60 cents per million tokens. The Enterprise Tier caters to organizations with sustained workloads, providing fine-tuned fashions, customized service degree agreements, and devoted help, with pricing accessible upon request.
Powering Cerebras Inference: The Wafer Scale Engine 3 (WSE-3)
On the coronary heart of Cerebras Inference is the Cerebras CS-3 system, powered by the industry-leading Wafer Scale Engine 3 (WSE-3). This AI processor is unmatched in its measurement and pace, providing 7,000 occasions extra reminiscence bandwidth than NVIDIA’s H100. The WSE-3’s huge scale allows it to deal with many concurrent customers, making certain blistering speeds with out compromising on efficiency. This structure permits Cerebras to sidestep the trade-offs that usually plague GPU-based techniques, offering best-in-class efficiency for AI workloads.
Seamless Integration and Developer-Pleasant API
Cerebras Inference is designed with builders in thoughts. It options an API that’s absolutely appropriate with the OpenAI Chat Completions API, permitting for straightforward migration with minimal code adjustments. This developer-friendly strategy ensures that integrating Cerebras Inference into current workflows is as seamless as doable, enabling fast deployment of high-performance AI functions.
Cerebras Methods: Driving Innovation Throughout Industries
Cerebras Methods isn’t just a pacesetter in AI computing but additionally a key participant throughout varied industries, together with healthcare, vitality, authorities, scientific computing, and monetary companies. The corporate’s options have been instrumental in driving breakthroughs at establishments such because the Nationwide Laboratories, Aleph Alpha, The Mayo Clinic, and GlaxoSmithKline.
By offering unmatched pace, scalability, and accuracy, Cerebras is enabling organizations throughout these sectors to sort out among the most difficult issues in AI and past. Whether or not it’s accelerating drug discovery in healthcare or enhancing computational capabilities in scientific analysis, Cerebras is on the forefront of driving innovation.
Conclusion: A New Period for AI Inference
Cerebras Methods is setting a brand new commonplace for AI inference with the launch of Cerebras Inference. By providing 20 occasions the pace of conventional GPU-based techniques at a fraction of the price, Cerebras is just not solely making AI extra accessible but additionally paving the way in which for the subsequent technology of AI functions. With its cutting-edge expertise, strategic partnerships, and dedication to innovation, Cerebras is poised to steer the AI {industry} into a brand new period of unprecedented efficiency and scalability.
For extra info on Cerebras Methods and to strive Cerebras Inference, go to www.cerebras.ai.
