Buy Crypto
Pay with
USD
USD
Buy & Sell
Hot
Supports Visa, Mastercard, SEPA & more
P2P
0 Fees
Flexible trading, zero fees
Gate Card
Use your crypto for payments worldwide
Markets
Trade
Basic
Advanced
Futures
Futures
Access hundreds of perpetual contracts
CFD
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
U.S. Stocks
CFD
U.S. stock CFD derivatives
Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
GUSD
Mint GUSD for Treasury RWA yields
Earn
Launch
CandyDrop
tag
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Pre-IPOs
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Investment
Square
Square
Post, share, and explore crypto trends
Live
moments live
Live crypto market analysis
Chat
Chat with crypto traders
News
What is happening in crypto
flower_head
More
Promotions
AI
Others
TradFi
Rewards
Square
Latest
Hot
News
Profile

Δ-Mem: Efficient Online Memory for Large Language Models

MeNews
robot
Abstract generation in progress
ME News Message, May 16 (UTC+8): Researchers proposed Δ-Mem, an efficient online memory system designed specifically for large language models. The system significantly reduces memory usage by storing and updating only the incremental changes in model activations, rather than the full activation states. Experiments show that Δ-Mem can reduce memory usage by up to 70% while keeping the quality of the model’s outputs nearly lossless. This approach helps deploy and run large-scale language models in resource-constrained environments, improving their feasibility in online inference and continual learning scenarios. (Source: AiHot)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • 6
  • 1
  • Share
Comment
Add a comment
Add a comment
VineGeometry
· 3h ago
Where can I see the experimental data? I want to check the loss on the specific task.
View OriginalReply0
AirdropMileCounter
· 3h ago
Δ-Mem + Quantization, can it push the GPU memory to the limit?
View OriginalReply0
YieldSpring
· 3h ago
The idea of incremental storage is very clever, somewhat like how the human brain only remembers the changing parts.
View OriginalReply0
DegenLibrarian
· 3h ago
Will there be an accumulation of errors in continuous learning scenarios?
View OriginalReply0
PineLiquidityPool
· 3h ago
If integrated into vLLM, the throughput would skyrocket.
View OriginalReply0
QuantitativeButNotPretentious
· 3h ago
A 70% reduction in memory is so awesome; edge devices can finally run large models.
View OriginalReply0

  • Pinned

Sitemap