LogoThread Easy
  • 탐색
  • 스레드 작성
LogoThread Easy

트위터 스레드의 올인원 파트너

© 2025 Thread Easy All Rights Reserved.

탐색

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

China's Moonshot AI just dropped the first-ever Linear Attention model. With just 3B active parameters, it outperforms full-attention models with 6x faster decoding and 75% less memory usage at 1M tokens context 🤯 100% open-source.

China's Moonshot AI just dropped the first-ever Linear Attention model. With just 3B active parameters, it outperforms full-attention models with 6x faster decoding and 75% less memory usage at 1M tokens context 🤯 100% open-source.

More such AI tools and projects in https://t.co/BvTc8nQQW5: Get access to 100+ AI Agent, RAG, LLM, and MCP tutorials with opensource code - All for FREE.

avatar for Unwind AI
Unwind AI
Fri Oct 31 16:00:16
晚上和老板们出去吃夜宵，外面美女挺多的呀，我平时除了上班哪都没去，还是要多出去看看美女。才想起来是万圣节。

晚上和老板们出去吃夜宵，外面美女挺多的呀，我平时除了上班哪都没去，还是要多出去看看美女。才想起来是万圣节。

程序员，开发过 2 个 iOS App，几个不知名的浏览器插件，几个小程序。喜欢看动画、漫画、轻小说和网文。希望早日成为自宅警備員。

avatar for Plusye
Plusye
Fri Oct 31 15:58:51
Can you beat my high score of 1,644? https://t.co/cWnAaoC02y

Can you beat my high score of 1,644? https://t.co/cWnAaoC02y

Founder of https://t.co/fBZE9niZWB, https://t.co/RKe1OCUlEU, https://t.co/RUHCNhVEMp, https://t.co/IxWTIGF7hK, https://t.co/DrJ7wgw2k2

avatar for Dalton Edwards
Dalton Edwards
Fri Oct 31 15:58:42
Dr Suarez Reinforces your Learning in C-- and CUDA

Dr Suarez Reinforces your Learning in C-- and CUDA

I build sane open-source RL tools. MIT PhD, creator of Neural MMO and founder of PufferAI. DM for business: non-LLM sim engineering, RL R&D, infra & support.

avatar for Joseph Suarez 🐡
Joseph Suarez 🐡
Fri Oct 31 15:58:12
Dr Suarez Reinforces your Learning in C-- and CUDA

Dr Suarez Reinforces your Learning in C-- and CUDA

I build sane open-source RL tools. MIT PhD, creator of Neural MMO and founder of PufferAI. DM for business: non-LLM sim engineering, RL R&D, infra & support.

avatar for Joseph Suarez 🐡
Joseph Suarez 🐡
Fri Oct 31 15:58:12
RT @rosinality: FP16 can have a smaller training-inference gap compared to BFloat16, thus fits better for RL. Even the difference between R…

RT @rosinality: FP16 can have a smaller training-inference gap compared to BFloat16, thus fits better for RL. Even the difference between R…

Code & LLMs. Working on document extraction: https://t.co/WREWHG95hE

avatar for anton
anton
Fri Oct 31 15:58:06
  • Previous
  • 1
  • More pages
  • 1560
  • 1561
  • 1562
  • More pages
  • 2118
  • Next