Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

We heavily optimized our GLTF files to fit any GPU memory. We built a custom Electron app to reduce polycount & convert textures to GPU-friendly Basis/ETC1S. Compressed textures used ~10-100x less memory & uploaded instantly, preventing decoding lags while scrolling!

Danetag's profile picture

Arnaud Tanielian

3,945 subscribers

17,465 görüntüleme • 6 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Introducing DuoAttention: Our new framework slashes both memory and latency for long-context LLMs without sacrificing performance! By applying full KV cache only to critical heads, we achieve: ⚡ 2.55x memory reduction ⚡ 2.18x decoding speedup ⚡ 3.3M tokens on a single A100 GPU
1:00

Introducing DuoAttention: Our new framework slashes both memory and latency for long-context LLMs without sacrificing performance! By applying full KV cache only to critical heads, we achieve: ⚡ 2.55x memory reduction ⚡ 2.18x decoding speedup ⚡ 3.3M tokens on a single A100 GPU

Guangxuan Xiao

31,023 görüntüleme • 1 yıl önce

Introducing VIBE CRAFTING! Add epic buildings, textures & creations into your HYTOPIA world instantly with just a prompt! Custom buildings, textures, creations and more are nearly instant with the help of AI & make creating HYTOPIA game worlds 100x easier!
4:06

Introducing VIBE CRAFTING! Add epic buildings, textures & creations into your HYTOPIA world instantly with just a prompt! Custom buildings, textures, creations and more are nearly instant with the help of AI & make creating HYTOPIA game worlds 100x easier!

HYTOPIA

16,897 görüntüleme • 1 yıl önce

Looking for a fast method to render your large-scale game components? Our lastest High-Perf Graphics paper allows to render terrains, oceans and even entire planets in realtime on any modern GPU using compute shaders. Fun fact: we use a Concurrent Binary Tree as a GPU memory manager.
0:40

Looking for a fast method to render your large-scale game components? Our lastest High-Perf Graphics paper allows to render terrains, oceans and even entire planets in realtime on any modern GPU using compute shaders. Fun fact: we use a Concurrent Binary Tree as a GPU memory manager.

Anis Benyoub

50,581 görüntüleme • 1 yıl önce

#VRChat guide on how to reduce download size and texture memory by optimizing textures. Super easy to do by literally anyone, with minimal effort. The jist is, REDUCE TEXTURE SIZES! most of your textures are probably wayyyy larger than is needed. Part 1/2
2:02

#VRChat guide on how to reduce download size and texture memory by optimizing textures. Super easy to do by literally anyone, with minimal effort. The jist is, REDUCE TEXTURE SIZES! most of your textures are probably wayyyy larger than is needed. Part 1/2

Liindy

38,410 görüntüleme • 2 yıl önce

We're presenting at #SIGGRAPH2025! 🚀 We use adaptive tetrahedral grids (via the LEB algorithm) to GPU path trace volumetric production assets. Fewer neighbors, less memory, real-time performance—up to 30× faster than regular grids.
0:57

We're presenting at #SIGGRAPH2025! 🚀 We use adaptive tetrahedral grids (via the LEB algorithm) to GPU path trace volumetric production assets. Fewer neighbors, less memory, real-time performance—up to 30× faster than regular grids.

Anis Benyoub

11,056 görüntüleme • 1 yıl önce

Eddie Jiao Drew To bring the imagery to life, we heavily optimized @LTXStudio's video model. Enough to stream live 1080p video at 24fps directly to your screen, connecting directly via websockets to Modal serverless GPU infra. (3/5)
0:19

Eddie Jiao Drew To bring the imagery to life, we heavily optimized @LTXStudio's video model. Enough to stream live 1080p video at 24fps directly to your screen, connecting directly via websockets to Modal serverless GPU infra. (3/5)

Zain Shah

227,717 görüntüleme • 2 ay önce

I built this little tool to optimize and re-export GLTF/GLB assets to GPU-compressed KTX2. It runs entirely client-side/in-browser. You can fiddle with the parameters, compare the before/after, and export to GLB. Try it here: #threejs #gamedev
0:30

I built this little tool to optimize and re-export GLTF/GLB assets to GPU-compressed KTX2. It runs entirely client-side/in-browser. You can fiddle with the parameters, compare the before/after, and export to GLB. Try it here: #threejs #gamedev

Simon

24,265 görüntüleme • 7 ay önce

Officially not skill issued in neovim anymore. I built the most memory-efficient file picker UI available in Neovim, and it's the first one to actually use async I/O for file previews. We allocate 3x less memory than the pure lua pickers while mainting custom binary and file index in memory.
1:05

Officially not skill issued in neovim anymore. I built the most memory-efficient file picker UI available in Neovim, and it's the first one to actually use async I/O for file previews. We allocate 3x less memory than the pure lua pickers while mainting custom binary and file index in memory.

Dmitriy Kovalenko

71,233 görüntüleme • 10 ay önce

Welcome to our first #AIonRTXHackathon! 🖥️ Your Objective: Build a custom Project G-Assist plug-in for a chance to win. 🏆 Prizes: GeForce RTX 5090 laptop, RTX 5080 GPU, RTX 5070 GPU. Details on registration, submissions, T&Cs, and more➡️
0:23

Welcome to our first #AIonRTXHackathon! 🖥️ Your Objective: Build a custom Project G-Assist plug-in for a chance to win. 🏆 Prizes: GeForce RTX 5090 laptop, RTX 5080 GPU, RTX 5070 GPU. Details on registration, submissions, T&Cs, and more➡️

NVIDIA RTX Spark

11,915 görüntüleme • 1 yıl önce

Another episode of the Godot PBR Mastery Series is out! Learn how to optimize 5 textures down to just 2, using Channel Packing! You can easily optimize textures by combining them using channel packing, reducing GPU and storage overhead. Full video in comments!
0:29

Another episode of the Godot PBR Mastery Series is out! Learn how to optimize 5 textures down to just 2, using Channel Packing! You can easily optimize textures by combining them using channel packing, reducing GPU and storage overhead. Full video in comments!

Foyezes

11,868 görüntüleme • 3 ay önce

Updated my GPU latency animation for the H100 today. Good to get an intuition for different memory areas.
0:44

Updated my GPU latency animation for the H100 today. Good to get an intuition for different memory areas.

Fleetwood

16,637 görüntüleme • 5 ay önce

🧠 Brain-Boosting Chinese Exercise to Sharpen Memory & Stay Fit Forever
1:07

🧠 Brain-Boosting Chinese Exercise to Sharpen Memory & Stay Fit Forever

Taichi for Health

227,270 görüntüleme • 1 yıl önce

Internally at NVIDIA, we use cuOpt based agentic workflows with agent skills to optimize our supply chains. Since it’s open source, you can too. With optimizations ready in minutes instead of weeks, the workflow uses multi-agent LangChain Deep agent orchestration and GPU-accelerated solvers to turn natural language into optimized decisions. Spin it up instantly with a Brev Launchable (preconfigured GPU environment) and grab free developer credits while they last.
4:46

Internally at NVIDIA, we use cuOpt based agentic workflows with agent skills to optimize our supply chains. Since it’s open source, you can too. With optimizations ready in minutes instead of weeks, the workflow uses multi-agent LangChain Deep agent orchestration and GPU-accelerated solvers to turn natural language into optimized decisions. Spin it up instantly with a Brev Launchable (preconfigured GPU environment) and grab free developer credits while they last.

NVIDIA AI

22,828 görüntüleme • 2 ay önce

Today I improved GPU Grass with a feature I call "batched instancing". It builds a grass batch at runtime and instances it. No world size increase, less GPU memory usage, runtime grass amount control, and better perf. 144 FPS with 11.2M grass triangles visible to the horizon!
0:47

Today I improved GPU Grass with a feature I call "batched instancing". It builds a grass batch at runtime and instances it. No world size increase, less GPU memory usage, runtime grass amount control, and better perf. 144 FPS with 11.2M grass triangles visible to the horizon!

RED_SIM

44,974 görüntüleme • 5 ay önce

I’m trying to re-texture my avatar in #EmoteLab it’s very cute! > Texture Cache > CoffeeBean > Custom Textures - Go back to EmoteLab and click Reload Textures. Method 2: Easier Way to Edit Textures Directly - Go to Settings → Open Character Folder. - Find the version you are using, then open your character folder. - Click Regions. - You will find the textures used by the character there. You can edit these textures directly as well. 💡Tip: I recommend editing the WeightTransfer folder first, then Click Unload Current Model and Load the model again to refresh the textures. Finally, You will get your own EmoteLab texture!!
1:22

I’m trying to re-texture my avatar in #EmoteLab it’s very cute! > Texture Cache > CoffeeBean > Custom Textures - Go back to EmoteLab and click Reload Textures. Method 2: Easier Way to Edit Textures Directly - Go to Settings → Open Character Folder. - Find the version you are using, then open your character folder. - Click Regions. - You will find the textures used by the character there. You can edit these textures directly as well. 💡Tip: I recommend editing the WeightTransfer folder first, then Click Unload Current Model and Load the model again to refresh the textures. Finally, You will get your own EmoteLab texture!!

B U N R I👾 @Live2D

21,771 görüntüleme • 4 ay önce

The UN estimates we dump a garbage truck’s worth of plastic into our oceans, rivers, & lakes every minute. Less than 10% of plastic is recycled because it’s made too cheaply to be used & reused.📉⬇️The best solution is to reduce, recycle and reuse ♻️ #ClimateAction
1:03

The UN estimates we dump a garbage truck’s worth of plastic into our oceans, rivers, & lakes every minute. Less than 10% of plastic is recycled because it’s made too cheaply to be used & reused.📉⬇️The best solution is to reduce, recycle and reuse ♻️ #ClimateAction

Eco Harmony Forum UG

39,515 görüntüleme • 5 ay önce

On the 13th day of #AtulSubhash tragic suicide, we gathered to pay tribute to his memory & reiterate our demand for #JusticeForAtulSubhash. We will continue to fight for justice & push for our demand of National Commission For Men in India. #AtulSubhashsuicidecase #JusticeIsDue
0:47

On the 13th day of #AtulSubhash tragic suicide, we gathered to pay tribute to his memory & reiterate our demand for #JusticeForAtulSubhash. We will continue to fight for justice & push for our demand of National Commission For Men in India. #AtulSubhashsuicidecase #JusticeIsDue

SIF Chandigarh

22,955 görüntüleme • 1 yıl önce

Here’s a demo of our Agentic Memory system, inspired by how our own brain holds information in a 3D spatial space. This feels, natural. Extending this further, we announced the Agentic Memory Protocol on July 15th in SF - which enables memory to be local, encrypted and available to other agents and apps based on your permission-only. We believe this is the future of memory - not owned by any one app, spatial, and always improving. Aaron Levie Andrej Karpathy
1:03

Here’s a demo of our Agentic Memory system, inspired by how our own brain holds information in a 3D spatial space. This feels, natural. Extending this further, we announced the Agentic Memory Protocol on July 15th in SF - which enables memory to be local, encrypted and available to other agents and apps based on your permission-only. We believe this is the future of memory - not owned by any one app, spatial, and always improving. Aaron Levie Andrej Karpathy

Varun

187,489 görüntüleme • 11 ay önce

Maybe we need to refresh all of una memory , me I no fit forget👍
1:04

Maybe we need to refresh all of una memory , me I no fit forget👍

cici💛

46,634 görüntüleme • 1 yıl önce