🚀 Introducing NSA: A Hardware-Aligned and Natively Trainable Sparse Attention mechanism for ultra-f... - 惯性聚合

推荐订阅源

LINUX DO - 最新话题

Proofpoint News Feed

Know Your Adversary

cs.CL updates on arXiv.org

Lohrmann on Cybersecurity

Darknet – Hacking Tools, Hacker News & Cyber Security

Security Latest

The Exploit Database - CXSecurity.com

Exploit-DB.com RSS Feed

Privacy & Cybersecurity Law Blog

Kaspersky official blog

The Last Watchdog

Threat Research - Cisco Blogs

Cyber Attacks, Cyber Crime and Cyber Security

WordPress大学

LINUX DO - 热门话题

OSCHINA 社区最新新闻

博客园 - Franky

Visual Studio Blog

Hacker News: Ask HN

Recent Commits to openclaw:main

Simon Willison's Weblog

Schneier on Security

Y Combinator Blog

Hackread – Cybersecurity News, Data Breaches, AI and More

Cybersecurity and Infrastructure Security Agency CISA

Fortinet All Blogs

CERT Recently Published Vulnerability Notes

The Blog of Author Tim Ferriss

Check Point Blog

Apple Machine Learning Research

有赞技术团队

人人都是产品经理

News and Events Feed by Topic

让小产品的独立变现更简单 - ezindie.com

Google Developers Blog

DeepSeek(@deepseek_ai)

We are making our discount permanent! 🎉 Enjoy building with DeepSeek-V4-Pro and bring your innovat... The DeepSeek-V4-Pro discount has been extended until May 31, 2026, 15:59 UTC! 🔥DeepSeek Input Cache Price Drop! Effective immediately, the price for input cache hits across the... 🔥DeepSeek-V4-Pro API is 75% OFF until May 5th, 2026, 15:59 (UTC Time)! Don't miss out on this massi... 🔹 Amid recent attention, a quick reminder: please rely only on our official accounts for DeepSeek n... API is Available Today! 🔹 Keep base_url, just update model to deepseek-v4-pro or deepseek-v4-flash... Structural Innovation & Ultra-High Context Efficiency 🔹 Novel Attention: Token-wise compression + ... DeepSeek-V4-Flash 🔹 Reasoning capabilities closely approach V4-Pro. 🔹 Performs on par with V4-Pro... DeepSeek-V4-Pro 🔹 Enhanced Agentic Capabilities: Open-source SOTA in Agentic Coding benchmarks. ... 🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M co... 🛠 Open Source Release 📦 DeepSeek-V3.2 Model: https://t.co/Kh8HzHl3uX 📦 DeepSeek-V3.2-Speciale Mo... 💻 API Update 🔹 V3.2: Same usage pattern as V3.2-Exp. 🔹 V3.2-Speciale: Served via a temporary end... 🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents! 🔹 D... ⚠️ Heads-up to anyone using the DeepSeek-V3.2-Exp inference demo: earlier versions had a RoPE implem... 🛠 Open Source Release 🔗 Model: https://t.co/kORJG3nCWN 🔗 Tech report: https://t.co/X8Wcqbhg5a ... 💻 API Update 🎉 Lower costs, same access! 💰 DeepSeek API prices drop 50%+, effective immediately.... 🚀 Introducing DeepSeek-V3.2-Exp — our latest experimental model! ✨ Built on V3.1-Terminus, it debu... 🚀 DeepSeek-V3.1 → DeepSeek-V3.1-Terminus The latest update builds on V3.1’s strengths while address... Introducing DeepSeek-V3.1: our first step toward the agent era! 🚀 🧠 Hybrid inference: Think & Non... 🚀 DeepSeek-R1-0528 is here! 🔹 Improved benchmark performance 🔹 Enhanced front-end capabilities ... 🚀 DeepSeek-V3-0324 is out now! 🔹 Major boost in reasoning performance 🔹 Stronger front-end devel... 🚀 Day 6 of #OpenSourceWeek: One More Thing – DeepSeek-V3/R1 Inference System Overview Optimized th... 🚀 Day 5 of #OpenSourceWeek: 3FS, Thruster for All DeepSeek Data Access Fire-Flyer File System (3FS... 🚀 Day 4 of #OpenSourceWeek: Optimized Parallelism Strategies ✅ DualPipe - a bidirectional pipeline... 🚀 Day 3 of #OpenSourceWeek: DeepGEMM Introducing DeepGEMM - an FP8 GEMM library that supports both... 🚀 Day 2 of #OpenSourceWeek: DeepEP Excited to introduce DeepEP - the first open-source EP communic... 🚀 Day 1 of #OpenSourceWeek: FlashMLA Honored to share FlashMLA - our efficient MLA decoding kernel... 🚀 Day 0: Warming up for #OpenSourceWeek! We're a tiny team @deepseek_ai exploring AGI. Starting n... 🎉 Excited to see everyone’s enthusiasm for deploying DeepSeek-R1! Here are our recommended settings... 🚀 DeepSeek-R1 is here! ⚡ Performance on par with OpenAI-o1 📖 Fully open-source model & techni... 🎉 Introducing DeepSeek App! 💡 Powered by world-class DeepSeek-V3 🆓 FREE to use with seamless int... DeepSeek has not issued any cryptocurrency. Currently, there is only one official account on the Twi... 🚀 Introducing DeepSeek-V3! Biggest leap forward yet: ⚡ 60 tokens/second (3x faster than V2!) 💪 En... 🚀 DeepSeek-R1-Lite-Preview is now live: unleashing supercharged reasoning power! 🔍 o1-preview-lev... 📢 After 3 months, the AI Mathematical Olympiad (AIMO) on Kaggle has announced the winners! 🎉 We'r... DeepSeek-Coder-V2: First Open Source Model Beats GPT4-Turbo in Coding and Math > Excels in coding a... 🚀 Launching DeepSeek-V2: The Cutting-Edge Open-Source MoE Model! 🌟 Highlights: > Places top 3 in ...

🚀 Introducing NSA: A Hardware-Aligned and Natively Trainable Sparse Attention mechanism for ultra-f...

DeepSeek (@d · 2025-02-18 · via DeepSeek(@deepseek_ai)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。