Back to News
ProductAI Understanding briefing

Positron AI Raises $875M Series C to Scale Memory-First Inference Systems

Positron AI announced an $875 million Series C financing at a $5 billion post-money valuation to scale its memory-first inference systems.

4 min readRead the primary source
Source-page capture accompanying Positron AI Raises $875M Series C to Scale Memory-First Inference Systems
Source referenceSource recorded
Publisher
hpcwire.com
Source link
hpcwire.comhttps://www.hpcwire.com/off-the-wire/positron-ai-raises-875m-series-c-to-scale-memory-first-inference-systems/
Source type
Linked source — primary-source status has not been established.
ContextUnderstand this in 60 seconds

Start here

Key terms

Memory (Agent Memory)
Stored context an AI agent uses across steps or sessions to improve continuity.
Inference
The runtime phase where a trained model generates predictions or outputs.
Compute
The processing resources required to train and run models, often measured in FLOPS or GPU hours.
Test yourselfWhat is AI? Quiz

What happened

Positron AI, a company that builds memory-first inference systems, has raised $875 million in a Series C financing round at a $5 billion post-money valuation. The funding will be used to scale the company's memory-first inference systems, including the production ramp of its next-generation inference system, Titan, and the tapeout of its next-generation silicon, Asimov. Asimov will pair Positron's compute architecture with 288 GB to 2,304 GB of memory per chip, and Titan will combine four to eight Asimov chips into a single system, designed to serve models beyond 16 trillion parameters and context windows beyond 10 million tokens in a single node.

Positron AI has raised $875 million in a Series C financing round at a $5 billion post-money valuation.

The funding will be used to scale the company's memory-first inference systems, including the production ramp of its next-generation inference system, Titan, and the tapeout of its next-generation silicon, Asimov.

Asimov will pair Positron's compute architecture with 288 GB to 2,304 GB of memory per chip, and Titan will combine four to eight Asimov chips into a single system, designed to serve models beyond 16 trillion parameters and context windows beyond 10 million tokens in a single node.

The company's energy-efficient architecture allows its systems to be deployed in air-cooled or liquid-cooled data centers at varying rack densities, without dependence on constrained HBM or CoWoS supply chains.

Positron AI's systems are already deployed at hyperscaler scale today, and the company is working with key partners such as Parasail, Jump Trading, and i3d.net to power their inference services.

Source details: hpcwire.com

Why it matters

The funding will enable Positron AI to scale its memory-first inference systems, which are designed to make AI inference dramatically cheaper and more energy efficient. This is particularly important as the center of gravity in AI is shifting from training models to running them, and serving that demand at scale is increasingly constrained by memory capacity, memory bandwidth, and power.

The funding will enable Positron AI to scale its memory-first inference systems, which are designed to make AI inference dramatically cheaper and more energy efficient.

This is particularly important as the center of gravity in AI is shifting from training models to running them, and serving that demand at scale is increasingly constrained by memory capacity, memory bandwidth, and power.

Positron AI's technology has the potential to impact various industries, including but not limited to, the AI industry, the data center industry, and the cloud computing industry.

The company's ability to scale its production and meet the demand for its systems will be crucial in determining the success of its memory-first inference systems.

The potential applications of Positron AI's technology in various industries will be an important factor in determining its impact on the AI industry.

What to watch next

The impact of Positron AI's memory-first inference systems on the AI industry, the company's ability to scale its production and meet the demand for its systems, and the potential applications of its technology in various industries.

The impact of Positron AI's memory-first inference systems on the AI industry.

The company's ability to scale its production and meet the demand for its systems.

The potential applications of Positron AI's technology in various industries.

The company's ability to deploy its systems in air-cooled or liquid-cooled data centers at varying rack densities.

The company's ability to work with key partners such as Parasail, Jump Trading, and i3d.net to power their inference services.

Related guides & quizzes

What is AI?ChatGPT & LLMsAI EthicsAI AgentsAI Models ExplainedTransformersFuture of AIAI TrainingPrompt EngineeringTest what you know — try a free AI quizLook up an AI term in our glossary
Found this useful?