Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

got cloud inference working! here i have smolvla running on a remote 4090 on prime intellect with a thin client running on my local pc sending observations to the remote server and receiving action chunks back. round trip latency is varying between 320-470ms! the 4090 instance I'm using is...

jackvial89's profile picture

Jack Vial

1,337 subscribers

12,992 Aufrufe • vor 5 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

One of the coolest uses of LM Studio and AI at AMD is using LM Link to have a Framework Desktop be a remote inference server for a laptop, including something little like Framework Laptop 12. It feels native on the laptop, but gets the desktop’s performance.
0:18

One of the coolest uses of LM Studio and AI at AMD is using LM Link to have a Framework Desktop be a remote inference server for a laptop, including something little like Framework Laptop 12. It feels native on the laptop, but gets the desktop’s performance.

Framework

39,030 Aufrufe • vor 4 Monaten

One of my go to activities when I'm on a field with many athletes and have minimal equipment. The pusher works his accel The resister works his decel Its feels awakward and unstable which is fine because their athletes not robots... #LTAD
0:12

One of my go to activities when I'm on a field with many athletes and have minimal equipment. The pusher works his accel The resister works his decel Its feels awakward and unstable which is fine because their athletes not robots... #LTAD

Jeremy Frisch

37,186 Aufrufe • vor 3 Jahren

I added a GUI file explorer to Loki C2! It’s not winning any design awards, but it works surprisingly well. The Loki C2 client is built with Electron. I got the explorer up and running in just a few hours—AI is killer for web dev tasks.
0:19

I added a GUI file explorer to Loki C2! It’s not winning any design awards, but it works surprisingly well. The Loki C2 client is built with Electron. I got the explorer up and running in just a few hours—AI is killer for web dev tasks.

Bobby Cooke

13,394 Aufrufe • vor 1 Jahr

Here is a comparison of the GWG for Oilers Kings on TNT (remote broadcast) and Sportsnet (in person)
0:27

Here is a comparison of the GWG for Oilers Kings on TNT (remote broadcast) and Sportsnet (in person)

Neil Pierre-Louis

1,007,493 Aufrufe • vor 1 Jahr

Got all 12 student plus 1 instructor Raspberry Pi Pico W with pimoroni GFX pack working and running my #redis streams #micropython workshop. Is this the most GFX Packs on a single project Hel Goblins ⚡🐍 vaporweave ? 😀 event is Thursday Oxford Python
0:15

Got all 12 student plus 1 instructor Raspberry Pi Pico W with pimoroni GFX pack working and running my #redis streams #micropython workshop. Is this the most GFX Packs on a single project Hel Goblins ⚡🐍 vaporweave ? 😀 event is Thursday Oxford Python

Simon Prickett 🇪🇺| simonprickett.dev

22,128 Aufrufe • vor 2 Jahren

Streaming iPhone data in real-time directly to Rerun 🚀 The collection process is one of the most frustrating parts of building imitation-learning datasets. I’ve got a little army of sensors—📱 iPhone, iPad, Quest 3—but getting them temporally aligned, spatially aligned, AND seeing real-time feedback while recording is tough. I stumbled on a great library from Cake Lab (WPI) called ARFlow. It’s a thin client built on Unity’s ARFoundation that connects over gRPC to a server running Rerun for live data logging. I forked it to: - Log the SLAM translation poses, and - Upgrade rerun to v0.23 for my use case. So far, it works well, but there are still a few hitches: 1. Right now, it’s solid on iPhone and iPad; my Quest 3 client is still slow and not super reliable. 2. I’m using an older ARFlow branch focused on real-time streaming only—no spatial or temporal sync yet. Unity builds for iOS keep failing. 🛠️ 3. Nothing is saved locally to the client, so packet loss is a risk on shaky networks. There’s huge potential in tapping the ubiquitous sensors we carry around every day, and ARFlow is a big step toward making that easy
0:16

Streaming iPhone data in real-time directly to Rerun 🚀 The collection process is one of the most frustrating parts of building imitation-learning datasets. I’ve got a little army of sensors—📱 iPhone, iPad, Quest 3—but getting them temporally aligned, spatially aligned, AND seeing real-time feedback while recording is tough. I stumbled on a great library from Cake Lab (WPI) called ARFlow. It’s a thin client built on Unity’s ARFoundation that connects over gRPC to a server running Rerun for live data logging. I forked it to: - Log the SLAM translation poses, and - Upgrade rerun to v0.23 for my use case. So far, it works well, but there are still a few hitches: 1. Right now, it’s solid on iPhone and iPad; my Quest 3 client is still slow and not super reliable. 2. I’m using an older ARFlow branch focused on real-time streaming only—no spatial or temporal sync yet. Unity builds for iOS keep failing. 🛠️ 3. Nothing is saved locally to the client, so packet loss is a risk on shaky networks. There’s huge potential in tapping the ubiquitous sensors we carry around every day, and ARFlow is a big step toward making that easy

Pablo Vela

27,383 Aufrufe • vor 1 Jahr

Running minecraft on a raspberry pi 5 with a circular screen hehe
0:15

Running minecraft on a raspberry pi 5 with a circular screen hehe

˗ˏˋmewtru´ˎ˗

32,751 Aufrufe • vor 3 Monaten

Switched to the Deere 3D nozzles. Running them on A and B on the exact apply. One is facing forward one is facing back. 20gpa. 10oz veltyma and an insecticide. Doing a great job with coverage.
0:14

Switched to the Deere 3D nozzles. Running them on A and B on the exact apply. One is facing forward one is facing back. 20gpa. 10oz veltyma and an insecticide. Doing a great job with coverage.

Jacob Wade

34,220 Aufrufe • vor 1 Jahr

I built a TV movie streaming app as well as a REMOTE CONTROLLER app to control the interface using your phone. This is a slight user experience bump for those who always lose their remote 😉 Testing on my monitor before I test on a TV. #ux
0:16

I built a TV movie streaming app as well as a REMOTE CONTROLLER app to control the interface using your phone. This is a slight user experience bump for those who always lose their remote 😉 Testing on my monitor before I test on a TV. #ux

DONNY WOMACK

58,885 Aufrufe • vor 3 Jahren

Working on a character as iconic as Optimus Prime was truly a dream come true. I'll always be grateful for the opportunity, especially as a huge Transformers fan. Here is a comparison between the viewport playblast and the final shot for one of his transformations.
0:14

Working on a character as iconic as Optimus Prime was truly a dream come true. I'll always be grateful for the opportunity, especially as a huge Transformers fan. Here is a comparison between the viewport playblast and the final shot for one of his transformations.

Rassoul Edji

43,344 Aufrufe • vor 1 Jahr

Gr00t-n1.5 is now available on phosphobot One click training and inference, all running in the cloud Example below with the instruction: "Grab food and place into bowl"
0:17

Gr00t-n1.5 is now available on phosphobot One click training and inference, all running in the cloud Example below with the instruction: "Grab food and place into bowl"

Frédéric Legrand

11,564 Aufrufe • vor 11 Monaten

This is Thumby, the worlds smallest game player which runs on Linux with a Raspberry Pi processor.
0:14

This is Thumby, the worlds smallest game player which runs on Linux with a Raspberry Pi processor.

Massimo

23,820 Aufrufe • vor 9 Monaten

Funny how you can do the same thing with a local model without sending all your data to a remote cloud.
0:18

Funny how you can do the same thing with a local model without sending all your data to a remote cloud.

Victor M

1,196,014 Aufrufe • vor 5 Monaten

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.
0:12

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.

stevibe

69,433 Aufrufe • vor 4 Monaten

Woow Tencent has released a model 100% open source which is better than Google Translate... And it runs locally on your phone?! - Only 440MB (!!) - 33 languages - On-device translation So we have now a local Google Translate which is running completely offline. They are using AngelSlim which their compression toolkit. That's why the model is so efficient.
0:12

Woow Tencent has released a model 100% open source which is better than Google Translate... And it runs locally on your phone?! - Only 440MB (!!) - 33 languages - On-device translation So we have now a local Google Translate which is running completely offline. They are using AngelSlim which their compression toolkit. That's why the model is so efficient.

Paul Couvert

141,760 Aufrufe • vor 2 Monaten

"Can I pass a zod schema from a server to a client component as a prop?" Nope, zod schema is not serializable. But you can re-import it in the client component.
0:19

"Can I pass a zod schema from a server to a client component as a prop?" Nope, zod schema is not serializable. But you can re-import it in the client component.

Alex Sidorenko

35,064 Aufrufe • vor 1 Jahr

The B-Wing Cockpit animation and model are done! I've been at this one for a while, and I'm relieved to have it finished, so I can move onto something else. Enjoy! Rendered in 3dsmax 2024 using VRay 7 GPU on a 4090 RTX. It took about 3-3.5m per frame.
0:15

The B-Wing Cockpit animation and model are done! I've been at this one for a while, and I'm relieved to have it finished, so I can move onto something else. Enjoy! Rendered in 3dsmax 2024 using VRay 7 GPU on a 4090 RTX. It took about 3-3.5m per frame.

Howie Day

57,483 Aufrufe • vor 1 Jahr

Dom Hamel is asked about his role with the Mets and his future position on the team: "I'm trying not to leave them a choice, I don't want to go back [to AAA] - I'm thinking I'm up here for a reason"
0:15

Dom Hamel is asked about his role with the Mets and his future position on the team: "I'm trying not to leave them a choice, I don't want to go back [to AAA] - I'm thinking I'm up here for a reason"

SNY Mets

81,585 Aufrufe • vor 11 Monaten

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang
0:11

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

LeRobot

24,727 Aufrufe • vor 1 Monat

This is only 1 Niagara emitter to handle thousands of decals as particles using Data Channels! Significantly lower overhead on the GameThread and only a single component per grid cell. This also adds instancing to the decals which is normally not supported for individual decal components. Working on this as part of data-oriented projectiles that run without Actors, asynchronous collision and supporting multiplayer (incl. client side prediction). Removes a huge amount of overhead from the CPU, more on that soon!
0:16

This is only 1 Niagara emitter to handle thousands of decals as particles using Data Channels! Significantly lower overhead on the GameThread and only a single component per grid cell. This also adds instancing to the decals which is normally not supported for individual decal components. Working on this as part of data-oriented projectiles that run without Actors, asynchronous collision and supporting multiplayer (incl. client side prediction). Removes a huge amount of overhead from the CPU, more on that soon!

Tom Looman

31,493 Aufrufe • vor 10 Monaten