LogoThread Easy
  • 探索
  • 線程創作
LogoThread Easy

Twitter 線程的一站式夥伴

© 2025 Thread Easy All Rights Reserved.

探索

Newest first — browse tweet threads

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

😂😂

😂😂

building and betting on the internet https://t.co/QBXKab06be https://t.co/nFbi7lK9XY

avatar for digital_literacy
digital_literacy
Fri Oct 31 22:42:39
First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.

Your guide to radiance fields | Host of the podcast @ViewDependent | Founder and CEO of https://t.co/5MjtfpwEU3 | discord: https://t.co/lrl64WGvlD

avatar for MrNeRF
MrNeRF
Fri Oct 31 22:41:17
RT @marc_louvion: It almost crashed my MacBook.. Happy Halloween 🎃👻

RT @marc_louvion: It almost crashed my MacBook.. Happy Halloween 🎃👻

🧑‍💻 https://t.co/Y30jsaHwz9 $20K/m ⚡️ https://t.co/vatLDmi9UG $17K/m 📈 https://t.co/3EDxln5mdi $16K/m ⭐️ https://t.co/MZc8tG9xWi $8K/m 🧬 https://t.co/SfrVXVtmdA $.5K/m 🍜 https://t.co/r07EpGSYJ2 $0K/m 🧾 https://t.co/7olaOzV8Xd $0/m +18 https://t.co/4zCWHGJp1S

avatar for Marc Lou
Marc Lou
Fri Oct 31 22:41:02
Hello from batting practice! 🧢🏆

Hello from batting practice! 🧢🏆

📈 Leading Growth @GroqInc 📌 Prev @a16z @HubSpot @TheHustle 💻 Chronically online: https://t.co/AkbwhoTr0K 📘 Wrote https://t.co/w1DBDrOZdI 🎙 Podcast at @sydlis 👇

avatar for Steph Smith
Steph Smith
Fri Oct 31 22:38:46
RT @TheOnion: ICE Agent, 7-Year-Old Both Wearing Same ‘Military Commando’ Halloween Costume https://t.co/Ui4Y7xFQkb

RT @TheOnion: ICE Agent, 7-Year-Old Both Wearing Same ‘Military Commando’ Halloween Costume https://t.co/Ui4Y7xFQkb

Research Scientist @meta (FAIR), Prof. @Unige_en, co-founder @nc_shape. I like reality.

avatar for François Fleuret
François Fleuret
Fri Oct 31 22:35:06
测试一下8443和443的效果， 结果还是443 速度最快。 --- 听得懂的肯定懂， 听不懂的就看评论区。

测试一下8443和443的效果， 结果还是443 速度最快。 --- 听得懂的肯定懂， 听不懂的就看评论区。

Growth Coach｜Helping creators build their personal brand on X 增长教练｜帮助创作者在X上打造个人品牌 公众号：PandaTalk8 X 增长群群主

avatar for Mr Panda
Mr Panda
Fri Oct 31 22:33:35
  • Previous
  • 1
  • More pages
  • 1509
  • 1510
  • 1511
  • More pages
  • 2111
  • Next