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
Stocks
CFD
U.S. stock CFD derivatives
US Stocks
Access real US stocks and ETFs
HK Stocks
Trade quality Hong Kong-listed stocks
Stock Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
IPO Access
Unlock full access to global stock IPOs
GUSD
Mint GUSD for Treasury RWA yields
Stocks Activities
Trade Popular Stocks and Unlock Generous Airdrops
Earn
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
IPO Access
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
2026 World Cup
Rewards

Sakana AI and Nvidia Achieve 30% Faster H100 Inference by Skipping 80% of Invalid Computations

GateNews
AI Industry News
Sakana AI and Nvidia have open-sourced TwELL, a sparse data format that enables H100 GPUs to skip 80% of invalid computations in large language models without sacrificing accuracy. The solution delivers up to 30% faster inference and 24% faster training on H100s while reducing peak memory usage. In testing on a 1.5-billion-parameter model, the approach reduced active neurons to below 2% through lightweight regularization during training, with no performance degradation across seven downstream tasks.
View Source
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.

Related News

05-10 04:13
Microsoft Open-Sources Phi-Ground 4B Model, Outperforms OpenAI Operator and Claude in Screen Clicking Accuracy
05-10 03:53
Tilde Research Discovers Muon Optimizer Kills 25% of Neurons; Aurora Alternative Achieves 100x Data Efficiency Gain
05-09 09:54
OpenAI's Reward System Inadvertently Scores Thinking Chains on 6 Models Including GPT-5.4
05-09 07:41
MiniMax Scans 200K Tokens, Discovers 4.9% Degradation in M2 Series Models
05-09 05:53
China Mobile Launches AI Model Platform with 300+ Integrations, Cuts Token Costs by 30%
In-Depth Analysis

NVIDIA’s open AI long-term partner Deepinfra raises $107 million Series B funding to build a “token factory”

ChainNewsAbmedia05-10 00:04

NVIDIA Space Computing ecosystem chain launches; Space-1 Vera Rubin delivers data-center-grade AI computing power to space

ChainNewsAbmedia05-09 16:13

Wall Street “AI chip generation shift”: Intel/AMD +25%, Micron +37%, NVIDIA lags behind

ChainNewsAbmedia05-09 00:39
Comment
0/400
No comments