Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

That's a hammer time again - just another prop from recent random scans - full PBR stack, automated capture, zero manual cleanup - just plug & play in your engine. We provide top quality 3D scanning services for games, film, fashion, and e-commerce.

McGavish

3,659 subscribers

19,476 Aufrufe • vor 1 Jahr •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

We can 3D scan even the hardest objects - dark, low-contrast, and nearly featureless surfaces are no longer a challenge - all with full PBR material stack. Need this level of precision for your production? Let me know! #photogrammetry #photometry

We can 3D scan even the hardest objects - dark, low-contrast, and nearly featureless surfaces are no longer a challenge - all with full PBR material stack. Need this level of precision for your production? Let me know! #photogrammetry #photometry

McGavish

45,203 Aufrufe • vor 1 Jahr

Introducing sigmaPBR - our new PBR solver which is currently in closed beta testing. sigmaPBR uses photometric images, camera poses, and input geometry to reconstruct accurate physically based material properties for use in rendering, ML training and 3D scanning pipelines.

Introducing sigmaPBR - our new PBR solver which is currently in closed beta testing. sigmaPBR uses photometric images, camera poses, and input geometry to reconstruct accurate physically based material properties for use in rendering, ML training and 3D scanning pipelines.

McGavish

27,326 Aufrufe • vor 1 Monat

Scanning large surface with PBR maps? No problem! Still polishing the methodologies and approach but initial tests are very promising. Here is a 130 x 50 cm tabletop, tricky reflective surface especially if we are aiming for smooth reconstruction.

Scanning large surface with PBR maps? No problem! Still polishing the methodologies and approach but initial tests are very promising. Here is a 130 x 50 cm tabletop, tricky reflective surface especially if we are aiming for smooth reconstruction.

McGavish

18,326 Aufrufe • vor 2 Jahren

How a 22-year-old developer built a full 3D Jet Ski racing game in just 40 minutes with zero manual coding He used Claude Opus 5 to generate physics, WebGL 3D graphics, HUD, and audio in a single prompt and turned single-prompt gamedev into a high-margin income stream. Costs: $423 He launched a single-prompt generation workflow that built the entire HTML5 project from scratch: Top layer: A Three.js and WebGL rendering pipeline dynamically creates 3D water physics, real-time wave dynamics, dynamic lighting, and jet ski fluid mechanics, all written autonomously inside one output file without external frameworks. Bottom layer: The Claude Opus 5 engine processed a massive 690-million-token context window to generate the complete gameplay logic, collision handling, dynamic sound generation, controls, and UI layout directly from a detailed initial system prompt. The trend of single-prompt 3D game creation is rapidly exploding across media and indie development. The author monetizes this tech stack through three main channels: 1. Viral Content & Media Systems: Short-form breakdown videos driving massive reach, monetized via promo placements, prompt-pack access, and private developer communities. 2. Rapid Hypercasual Prototyping: Testing 10+ WebGL mechanics per day, flipping fully functional browser games on itch io or CodeCanyon, and licensing prototypes directly to casual game portals. 3. Interactive WebGL Client Solutions: Delivering custom 3D promotional browser games and interactive brand experiences for clients in 48 hours instead of weeks. First month results: > WebGL games generated: 24 > Viral impressions generated: 3.8M+ > Total revenue across licensing & content: $21,400 The AI completely automated the core development lifecycle: Claude Opus 5 built the physics engine, rendered 3D graphics in WebGL, hooked up audio controllers, and generated interactive browser logic with zero manual line-by-line coding. Bookmark it and check article 👇

Ridark

11,592 Aufrufe • vor 2 Monaten

New scan sample, old wooden container scanned using our advanced robotic scanner developed at INVOLV3D and inciprocal software for PBR material processing. You can literally smell this wood! #3dscanning #pbr #b3d

New scan sample, old wooden container scanned using our advanced robotic scanner developed at INVOLV3D and inciprocal software for PBR material processing. You can literally smell this wood! #3dscanning #pbr #b3d

McGavish

12,902 Aufrufe • vor 2 Jahren

we just hit 100,000 wishlists on steam. this feels surreal. thank you everyone for your support. six months after we announced. zero marketing budget. full development funded from my own savings. undead chronicles is the zombie game I personally always wanted to play, that's my aim to create. no hud. no crosshair. no waypoints. no co-op. no jokes. just slow zombies, and a banker who has never held a gun.

we just hit 100,000 wishlists on steam. this feels surreal. thank you everyone for your support. six months after we announced. zero marketing budget. full development funded from my own savings. undead chronicles is the zombie game I personally always wanted to play, that's my aim to create. no hud. no crosshair. no waypoints. no co-op. no jokes. just slow zombies, and a banker who has never held a gun.

Undead Chronicles

12,382 Aufrufe • vor 2 Monaten

🔥 We just shipped a full end-to-end character animation platform 🔥 Here's the full rundown: AI Auto-Rig your character meshes. Text-Generate new characters from your brain with our Luma Genie integration. Store your characters for easy access. Apply 1,000+ animations from our library to your characters. Upload and visualize your own motion data from any motion capture source Use your MoCap data on any character in any 3D program All on HEAT More below 👇

🔥 We just shipped a full end-to-end character animation platform 🔥 Here's the full rundown: AI Auto-Rig your character meshes. Text-Generate new characters from your brain with our Luma Genie integration. Store your characters for easy access. Apply 1,000+ animations from our library to your characters. Upload and visualize your own motion data from any motion capture source Use your MoCap data on any character in any 3D program All on HEAT More below 👇

HEAT

24,973 Aufrufe • vor 2 Jahren

'Member how back in the day you could just pop a cartridge or disc in your console and play a game? Kid has been waiting for me to get home from work all day so we could play Street Fighter 6, and it's a 90 GIGAFUGGINBYTE DOWNLOAD? I have fiber internet, hardwired to the X-Box, talm'out being ready at breakfast time tomorrow. Physical games aren't even physical games anymore. Send me back to 1998.

'Member how back in the day you could just pop a cartridge or disc in your console and play a game? Kid has been waiting for me to get home from work all day so we could play Street Fighter 6, and it's a 90 GIGAFUGGINBYTE DOWNLOAD? I have fiber internet, hardwired to the X-Box, talm'out being ready at breakfast time tomorrow. Physical games aren't even physical games anymore. Send me back to 1998.

Tusk 🦣

428,187 Aufrufe • vor 4 Monaten

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github

is it legal? NVIDIA and Microsoft just open-sourced the pieces of a full 3D studio for Opus 5.5 15 github repos, sorted by what you want to make: GENERATE 3D ASSETS 01. TRELLIS.2 by Microsoft: -> one image in, a fully textured 3D asset out, about 3 seconds on an H100 02. Hunyuan3D-2.1 by Tencent: -> production-ready 3D assets with PBR textures 03. stable-fast-3d by Stability AI: -> one photo to a clean UV-unwrapped mesh, built for speed 04. meshy-mcp-server by Meshy: -> text or image to 3D, then remesh, retexture, rig and animate from your agent BUILD SCENES AND WORLDS 05. mcp-for-blender: -> prompt-driven modeling, scene building and edits in a live Blender 06. HY-World-2.0 by Tencent: -> text or a single image to a navigable 3D world 07. supersplat by PlayCanvas: -> inspect, edit, optimize and publish 3D Gaussian splats in the browser 08. kit-usd-agents by NVIDIA: -> edit Omniverse USD scenes in plain English, plus MCP servers for Kit and Isaac Sim MAKE A GAME 09. unity-mcp: -> run the Unity Editor in plain English: scenes, C# scripts, assets, tests, builds 10. godot-ai: -> 46 tools for a live Godot editor: scenes, scripts, signals, UI, particles 11. unreal-engine-mcp: -> drive a live Unreal Editor: actors, world building, Blueprints 3D ON THE WEB 12. editor-mcp-server by PlayCanvas: -> your agent builds PlayCanvas scenes and checks they actually run 13. three.js: -> the JavaScript 3D library itself, 115k stars on GitHub 14. react-three-fiber: -> build three.js scenes as reusable React components 15. threejs-skills: -> 10 three.js skills for Claude Code, from shaders to post-processing a full 3D pipeline, and every piece of it lives on github

Mnimiy

170,687 Aufrufe • vor 2 Tagen

In the summer of 2023, I cold emailed Jensen Huang and asked to capture a NeRF of him at SIGGRAPH. He responded in about an hour and said yes. A radiance field is, in the simplest terms, akin to a 3D photograph. A moment in time, so completely reconstructed that you can move through it and see it from angles the original cameras never occupied. NeRFs were the original method. Gaussian splatting, which debuted at that same SIGGRAPH, has since become the dominant form of radiance field. I called my late friend James, who told me we needed to begin practicing immediately. We ran capture after capture for weeks until we consistently got the capture time down to ~30 seconds with one camera. Later, in a hallway at the LA Convention Center during SIGGRAPH, I captured the portrait you're seeing now, a full 360° gaussian splat of Jensen, rendered here as a 2D flythrough. Afterward, I continued the conversation with him and members of his team to make the case for radiance fields as a foundational representation for imaging. To my surprise, they listened. Three years later, NVIDIA has several works, including NuRec, fVDB, 3DGRUT, and gsplat all utilizing radiance fields. The landscape has evolved enough that the reasoning is obvious. Gaussian splatting has begun to ship across some of the world’s largest industries, including autonomous vehicles, AEC, geospatial, media and entertainment, robotics, e-commerce, hospitality. It’s become clear that lifelike 3D is here to stay. And yet I think we will look back and be disappointed by how late we started taking 3D portraits of the people around us, just like how we have sparse 2D photos of our grandparents and great grandparents. We have billions of photographs of the people we know and love, but almost no radiance fields of them. I'll be returning to SIGGRAPH in LA where this was initially captured three years ago, with the landscape looking significantly different. Radiance fields are more under deployed than ever relative to what they can do. I'm excited for the future of imaging, and for 2D to transition into 3D. I have a few things up my sleeve that I think will make that case plainly.

In the summer of 2023, I cold emailed Jensen Huang and asked to capture a NeRF of him at SIGGRAPH. He responded in about an hour and said yes. A radiance field is, in the simplest terms, akin to a 3D photograph. A moment in time, so completely reconstructed that you can move through it and see it from angles the original cameras never occupied. NeRFs were the original method. Gaussian splatting, which debuted at that same SIGGRAPH, has since become the dominant form of radiance field. I called my late friend James, who told me we needed to begin practicing immediately. We ran capture after capture for weeks until we consistently got the capture time down to ~30 seconds with one camera. Later, in a hallway at the LA Convention Center during SIGGRAPH, I captured the portrait you're seeing now, a full 360° gaussian splat of Jensen, rendered here as a 2D flythrough. Afterward, I continued the conversation with him and members of his team to make the case for radiance fields as a foundational representation for imaging. To my surprise, they listened. Three years later, NVIDIA has several works, including NuRec, fVDB, 3DGRUT, and gsplat all utilizing radiance fields. The landscape has evolved enough that the reasoning is obvious. Gaussian splatting has begun to ship across some of the world’s largest industries, including autonomous vehicles, AEC, geospatial, media and entertainment, robotics, e-commerce, hospitality. It’s become clear that lifelike 3D is here to stay. And yet I think we will look back and be disappointed by how late we started taking 3D portraits of the people around us, just like how we have sparse 2D photos of our grandparents and great grandparents. We have billions of photographs of the people we know and love, but almost no radiance fields of them. I'll be returning to SIGGRAPH in LA where this was initially captured three years ago, with the landscape looking significantly different. Radiance fields are more under deployed than ever relative to what they can do. I'm excited for the future of imaging, and for 2D to transition into 3D. I have a few things up my sleeve that I think will make that case plainly.

Radiance Fields

18,084 Aufrufe • vor 4 Monaten

New scan, new quality #b3d

New scan, new quality #b3d

McGavish

87,453 Aufrufe • vor 3 Jahren

We are building the home of the doge economy Projects across every major vertical are already gearing up to launch on DogeOS. Builders are cooking. Here's what the community should be excited to explore.... Much Thoughts ✍️ Very 🐕 So Soon... 💱 DeFi Swaps, lending, yield, memes all running on DogeOS with Dogecoin at the heart of it all. This means the most beloved and recognized asset in crypto finally gets a real financial system built around it. Doge stops being just a vibe and starts being productive. The community has been asking for this for years. 🎮 Gaming On-chain games built on DogeOS: play, compete, unlock with Dogecoin. Doge was born from meme and gaming culture. Bringing games on-chain is just Doge coming home. Play to unlock, play to grow, play because it's fun. Gaming is one of the strongest onramps in all of crypto. It's how you turn curious onlookers into active participants. This is a chance to bring the fun and the love of this community to a whole new wave of users, and remind the old ones why they fell in love with Doge in the first place. 🤖 AI Builders are already positioned to ship AI powered dApps, agents, and tools natively on DogeOS. Think automated trading agents, AI assistants that manage your wallet, dApp builders, and solutions that get smarter the more the ecosystem grows. Agents benefit from fast and cheap transaction environments, and that's exactly what DogeOS is built for. DogeOS becomes the rails for the next wave of on-chain AI, with Doge as the fuel. 📣 Community and Social Apps built for the culture. Social tools, creator platforms, community coordination, all on-chain and all for the Doge economy. Dogecoin has always had the strongest community in crypto. Now that community gets its own social layer instead of living as a guest in another chain's world. Dogecoin should be the focal point, not just another asset being served. 🐕 All your desires. One ecosystem. We are building toward the future this community has dreamt of, making Dogecoin the central piece of a real on-chain economy. This is just the start. Much building. Prepare your paws.

We are building the home of the doge economy Projects across every major vertical are already gearing up to launch on DogeOS. Builders are cooking. Here's what the community should be excited to explore.... Much Thoughts ✍️ Very 🐕 So Soon... 💱 DeFi Swaps, lending, yield, memes all running on DogeOS with Dogecoin at the heart of it all. This means the most beloved and recognized asset in crypto finally gets a real financial system built around it. Doge stops being just a vibe and starts being productive. The community has been asking for this for years. 🎮 Gaming On-chain games built on DogeOS: play, compete, unlock with Dogecoin. Doge was born from meme and gaming culture. Bringing games on-chain is just Doge coming home. Play to unlock, play to grow, play because it's fun. Gaming is one of the strongest onramps in all of crypto. It's how you turn curious onlookers into active participants. This is a chance to bring the fun and the love of this community to a whole new wave of users, and remind the old ones why they fell in love with Doge in the first place. 🤖 AI Builders are already positioned to ship AI powered dApps, agents, and tools natively on DogeOS. Think automated trading agents, AI assistants that manage your wallet, dApp builders, and solutions that get smarter the more the ecosystem grows. Agents benefit from fast and cheap transaction environments, and that's exactly what DogeOS is built for. DogeOS becomes the rails for the next wave of on-chain AI, with Doge as the fuel. 📣 Community and Social Apps built for the culture. Social tools, creator platforms, community coordination, all on-chain and all for the Doge economy. Dogecoin has always had the strongest community in crypto. Now that community gets its own social layer instead of living as a guest in another chain's world. Dogecoin should be the focal point, not just another asset being served. 🐕 All your desires. One ecosystem. We are building toward the future this community has dreamt of, making Dogecoin the central piece of a real on-chain economy. This is just the start. Much building. Prepare your paws.

DogeOS

43,197 Aufrufe • vor 1 Monat

🚨 Attention Community! It's Time to Act! 🚨 Fellow players, we've been patient, but now it's time to stand up against the unfair practices of the Hamster Kombat (HK) team. Here's what's been happening: 1. 📱 Games flooded with low-quality ads 2. 🏆 Random "cheater" achievements without explanation 3. 💸 Airdrop denial - many of us got ZERO rewards We warned about these unfair practices, but our voices were ignored. Now, it's time for action! 🦾 Our Plan of Resistance: 1. 🚫 Block Hamster Kombat_bot 2. ❌ Unsubscribe from Hamster Kombat and all their social media 3. 🙅‍♂️ Stop watching their YouTube videos and reading their news Remember: WE are the community. WE made them successful. It's time to show them we're not just hamsters in their wheel! ⏳ Time is of the Essence! We have a short window before the final coin distribution. Let's make our voices heard: - 📣 Complain and block Hamster Kombat_bot - 👋 Unsubscribe from Hamster Kombat Only by standing together can we hope to effect change. If we reduce their subscriber count and views, they might realize that their current approach won't work for Season 2. 💪 Join the Resistance! United, we can send a clear message: treat your community fairly, or lose your community entirely. 📢 Spread the Word! - 🔁 Repost this message to your channels and groups - 📲 Share with your friends who play #Hamster_Kombat - 💬 Discuss this in your gaming communities The more people who join our cause, the stronger our message will be! Share this post, spread the word, and let's show them the true power of our hamster army! 🐹✊ #HamsterRevolution #FairPlayForAll #HKResistance #ShareAndRepost #Scam #hamster_Kombat_boycott #HAMSTERKOMBATSCAM

🚨 Attention Community! It's Time to Act! 🚨 Fellow players, we've been patient, but now it's time to stand up against the unfair practices of the Hamster Kombat (HK) team. Here's what's been happening: 1. 📱 Games flooded with low-quality ads 2. 🏆 Random "cheater" achievements without explanation 3. 💸 Airdrop denial - many of us got ZERO rewards We warned about these unfair practices, but our voices were ignored. Now, it's time for action! 🦾 Our Plan of Resistance: 1. 🚫 Block Hamster Kombat_bot 2. ❌ Unsubscribe from Hamster Kombat and all their social media 3. 🙅‍♂️ Stop watching their YouTube videos and reading their news Remember: WE are the community. WE made them successful. It's time to show them we're not just hamsters in their wheel! ⏳ Time is of the Essence! We have a short window before the final coin distribution. Let's make our voices heard: - 📣 Complain and block Hamster Kombat_bot - 👋 Unsubscribe from Hamster Kombat Only by standing together can we hope to effect change. If we reduce their subscriber count and views, they might realize that their current approach won't work for Season 2. 💪 Join the Resistance! United, we can send a clear message: treat your community fairly, or lose your community entirely. 📢 Spread the Word! - 🔁 Repost this message to your channels and groups - 📲 Share with your friends who play #Hamster_Kombat - 💬 Discuss this in your gaming communities The more people who join our cause, the stronger our message will be! Share this post, spread the word, and let's show them the true power of our hamster army! 🐹✊ #HamsterRevolution #FairPlayForAll #HKResistance #ShareAndRepost #Scam #hamster_Kombat_boycott #HAMSTERKOMBATSCAM

Pioneer

43,473 Aufrufe • vor 2 Jahren

We have the huge honor of having KIRO selected in the TOP 50 of the #FutureVisionXPRIZE , among thousands of trailers submitted from all over the world. So we thought this was the perfect time to show you how we created one of the most visual effects in the trailer: ZERO GRAVITY. And no… we didn’t have a zero-gravity plane. We had a swimming pool. 😂 This was an idea I’d been thinking about for a long time: shooting underwater to simulate weightlessness. Obviously, underwater ≠ zero gravity. But it gave us something incredibly valuable: freedom of movement. Our protagonist could float, spin, push another crew member away, drift through the frame… Doing all of that practically on our budget would have been almost impossible. Our alternatives were basically: → create the entire sequence with AI → or find another practical way to fake physics So we went underwater. One of our biggest debates was actually… her hair. From a narrative perspective, it would probably make more sense for an astronaut working inside a spacecraft to have her hair tied up — or even wear some kind of helmet. But visually? Loose hair floating in zero gravity is just WAY more cinematic. It instantly sells the sensation of weightlessness. So we knowingly sacrificed a little realism in favor of a stronger image. And I’d make that decision again. There are actually several shots from this experiment that I really love but we couldn’t include because of the trailer’s runtime. I have a feeling this won’t be the last time we use this technique. Here’s the before & after. 👇

We have the huge honor of having KIRO selected in the TOP 50 of the #FutureVisionXPRIZE , among thousands of trailers submitted from all over the world. So we thought this was the perfect time to show you how we created one of the most visual effects in the trailer: ZERO GRAVITY. And no… we didn’t have a zero-gravity plane. We had a swimming pool. 😂 This was an idea I’d been thinking about for a long time: shooting underwater to simulate weightlessness. Obviously, underwater ≠ zero gravity. But it gave us something incredibly valuable: freedom of movement. Our protagonist could float, spin, push another crew member away, drift through the frame… Doing all of that practically on our budget would have been almost impossible. Our alternatives were basically: → create the entire sequence with AI → or find another practical way to fake physics So we went underwater. One of our biggest debates was actually… her hair. From a narrative perspective, it would probably make more sense for an astronaut working inside a spacecraft to have her hair tied up — or even wear some kind of helmet. But visually? Loose hair floating in zero gravity is just WAY more cinematic. It instantly sells the sensation of weightlessness. So we knowingly sacrificed a little realism in favor of a stronger image. And I’d make that decision again. There are actually several shots from this experiment that I really love but we couldn’t include because of the trailer’s runtime. I have a feeling this won’t be the last time we use this technique. Here’s the before & after. 👇

Esteban Diba

34,069 Aufrufe • vor 1 Monat

Throughout my journey in developing multimodal models, I’ve always wanted a framework that lets me plug & play modality encoders/decoders on top of an auto-regressive LLM. I want to prototype fast, try new architectures, and have my demo files scale effortlessly — with full support for parallelism and optimization. Not just to hack⚙️, but also to scale🚀. So finally we built it for ourselves. LMMs-Engine: a lean, efficient framework built to train unified multimodal model at scale. From Qwen LLM, VLM, LLaVA-OV, and WanVideo, to unified models like Qwen-Omni and BAGEL — plus Linear-Attn GDN and research prototypes like RAE and SiT - all under one modular system that seamlessly integrates diverse datasets and optimization strategies. Powered by FSDP2 multi-dim parallelism, Ulysses sequence parallel, Flash-Attention, Liger Kernels, and Native Sparse Attention (also with bonus support for the Muon optimizer for all models).

Throughout my journey in developing multimodal models, I’ve always wanted a framework that lets me plug & play modality encoders/decoders on top of an auto-regressive LLM. I want to prototype fast, try new architectures, and have my demo files scale effortlessly — with full support for parallelism and optimization. Not just to hack⚙️, but also to scale🚀. So finally we built it for ourselves. LMMs-Engine: a lean, efficient framework built to train unified multimodal model at scale. From Qwen LLM, VLM, LLaVA-OV, and WanVideo, to unified models like Qwen-Omni and BAGEL — plus Linear-Attn GDN and research prototypes like RAE and SiT - all under one modular system that seamlessly integrates diverse datasets and optimization strategies. Powered by FSDP2 multi-dim parallelism, Ulysses sequence parallel, Flash-Attention, Liger Kernels, and Native Sparse Attention (also with bonus support for the Muon optimizer for all models).

Brian Li

54,957 Aufrufe • vor 11 Monaten