Micron Develops Physical AI Edge Inference Memory EIM Expected to Mass Produce in 2028
Micron Technology is developing a physical AI edge inference memory (EIM), which is expected to begin mass production in the second half of 2028. This product will be used in LPDDR6 to meet the demand for low-power DRAM in autonomous driving and humanoid robots. Micron is in discussions with major customers regarding the related products. EIM sits between AI chips and memory, processing inference data at high speed by stacking LPDDR on logic chips, although the computing architecture has not been fully disclosed. Micron's Vice President, Li Zhe, stated that the current parameters for robotic AI models range from 1 billion to 2 billion, with low bandwidth requirements. However, as more advanced visual language models emerge, LPDDR will not be sufficient to meet the demand, and HBM will ultimately be used for humanoid robots. Micron anticipates that future high-performance humanoid robots will require about 200 GB of DRAM and 4 TB of storage, while current service robots require approximately 12 GB of DRAM and 256 GB of storage. Micron's CEO, Sanjay Mehrotra, pointed out that the storage capacity of a humanoid robot is about 10 times that of a typical L2+ passenger vehicle. The storage industry is expected to enter a period of sustained demand growth for several decades around 2030, driven by the need to simultaneously process data from hundreds of sensors and run large models for millisecond-level control locally. Counterpoint Research estimates that global DRAM demand for humanoid robots will increase from 8,300 Tbit to 172,000 Tbit.
-- Price
This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.
You may also like

Microsoft's Exit from Nscale Partnership May Benefit Nebius, IREN and Other Computing Power Suppliers

QCP: AI Credit Risk Heats Up, Bitcoin May Face Range Breakthrough

PAPER Token Mining Rewards Drop by Nearly 90%, Facing Potential Sell Pressure

French National Assembly Passes Tax Amendment on Stablecoin Transactions, Effective 2027

Three Men Jailed for Home Invasion Attempting Crypto Theft

Bitcoin miner stocks driven by AI sentiment, not BTC prices

Black Monday Posts Break Records

Bitcoin Recovery Faces Challenges as Exchange Reserves Rise and Spot Demand Turns Negative

Phala Cloud Attacked, Some Customer Logs and Environment Variables Read

Freezing and Confiscation of Cryptos: Europe Strengthens Cooperation Against Criminal Networks

Cathie Wood Bullish on Memory Chips, Bank of America Warns It's Not Time to Buy Risk Assets

Chinese Sell-Side Analysis: AI Hardware Faces High Volatility Risks

JPMorgan Expands JPM Coin to Ethereum Network

Peter Schiff Predicts Bitcoin Crash Over 99%

Justin Sun Discusses 'Sunology': Combining Game Theory and Evolutionary Theory to Help Young People Achieve Zero to One

World launches biometric checks on Zoom to tackle AI deepfakes

World ID by Sam Altman Available for Zoom and Banks

Ripple Executive States DeFi Will Open Up to the Masses

FSS and FIU Discuss Stronger Crypto Oversight Framework

Tokenized Stocks: 9 Companies Oppose OKX-ICE, Nasdaq Withdraws

JPMorgan Analysis: The Recent AI Stock Plunge May Not Rebound as Quickly as in July

Taiwan Halts Trading on Coinbase and Kalshi Ahead of Local Elections Due to Election Gambling Reasons

Crypto: 107 incidents and $1.18 billion stolen in Q3 2026

Korean Financial Regulator Apologizes for the Listing of Single Stock Leveraged ETFs

Financial Supervisory Service Chief Acknowledges Lack of Capability to Address Cryptocurrency Fraud

XRP Ledger bug-fix patch set for Oct. 23 with 29 validators support

Global Economic Resilience Faces Test as High Rates and Supply Risks Impact Asset Allocation

Japan's Three Major Megabanks Complete Joint Issuance of Stablecoins and International Payment Demonstration—Preparing for Corporate Issuance

Morgan Stanley Recommends Up to 4% in Cryptocurrencies for Aggressive Portfolios




