正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Kimi K3 is out. 2.8T parameters. 1.4 TB of weights, frontier-level performance. Serving it on your own infra is the hard part - you need multi-node inference spread across every cluster you can grab capacity from. And then autoscaling, cache-aware routing, PD disaggregation - an entire serving stack around... show more

SkyPilot

6,124 subscribers

14,478 次观看 • 19 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

underrated gems in Kimi-K3 release: > an early K3 wrote the majority of the kernels in the late development stages > it built a triton-class compiler from scratch, MiniTriton, that delivers performance on par with or better than Triton and torch.compile > then it designed a chip, by a model, for a model, in one 48-hour autonomous run the model is rewriting and optimizing every layer of the stack it runs on: kernels for its own training. A compiler for its own kernels. silicon for its own weights. we're watching software build its own hardware

underrated gems in Kimi-K3 release: > an early K3 wrote the majority of the kernels in the late development stages > it built a triton-class compiler from scratch, MiniTriton, that delivers performance on par with or better than Triton and torch.compile > then it designed a chip, by a model, for a model, in one 48-hour autonomous run the model is rewriting and optimizing every layer of the stack it runs on: kernels for its own training. A compiler for its own kernels. silicon for its own weights. we're watching software build its own hardware

Alex Ker 🔭

310,544 次观看 • 1 个月前

With Kimi K3 Day-0 on vLLM: Open Frontier Intelligence for Everyone 🚀 At 2.8 trillion parameters, Moonshot AI's Kimi K3 is one of the most powerful open-weight models ever released. Starting today, you can serve it on vLLM the moment the weights are public. What K3 brings: 🧠 2.8T-parameter Mixture-of-Experts (16 of 896 experts active per token) 📚 1M-token context window 🛠️ Native multimodal understanding, including vision ⚡ Kimi Delta Attention: a hybrid of linear and full attention that makes million-token context affordable Huge thank you to Kimi.ai AI for the model release and partnership, Inferact for leading the vLLM optimizations, and to our partners at NVIDIA, AMD, and the broader vLLM community. 1/6

With Kimi K3 Day-0 on vLLM: Open Frontier Intelligence for Everyone 🚀 At 2.8 trillion parameters, Moonshot AI's Kimi K3 is one of the most powerful open-weight models ever released. Starting today, you can serve it on vLLM the moment the weights are public. What K3 brings: 🧠 2.8T-parameter Mixture-of-Experts (16 of 896 experts active per token) 📚 1M-token context window 🛠️ Native multimodal understanding, including vision ⚡ Kimi Delta Attention: a hybrid of linear and full attention that makes million-token context affordable Huge thank you to Kimi.ai AI for the model release and partnership, Inferact for leading the vLLM optimizations, and to our partners at NVIDIA, AMD, and the broader vLLM community. 1/6

vLLM

102,101 次观看 • 19 天前

$50 IN FREE CREDITS FOR GLM 5.2, KIMI K3 AND DEEPSEEK V4 PRO, ON A CODE THE COMPANY PUBLISHED ITSELF • ai&, the inference layer > Frontier models at up to 80% lower cost: > GLM 5.2, Kimi K3, Kimi K2.7 Code, DeepSeek V4 Pro and V4 Flash, plus Qwen3.6 27B, Gemma 4 31B and gpt-oss-120b. > OpenAI-compatible endpoint, so it drops into any agent or IDE you already run. • where the discount comes from > They route across AMD, NVIDIA and Tenstorrent, sending each workload to the silicon that suits it. > Everyone else tunes on one kind of chip, so the saving is architectural rather than promotional. Claiming it -> Credits in the top right, pick $50, apply "UNITABETAI" at checkout. The code has been live since their June launch, so run it on your own account before you plan around it ↓

$50 IN FREE CREDITS FOR GLM 5.2, KIMI K3 AND DEEPSEEK V4 PRO, ON A CODE THE COMPANY PUBLISHED ITSELF • ai&, the inference layer > Frontier models at up to 80% lower cost: > GLM 5.2, Kimi K3, Kimi K2.7 Code, DeepSeek V4 Pro and V4 Flash, plus Qwen3.6 27B, Gemma 4 31B and gpt-oss-120b. > OpenAI-compatible endpoint, so it drops into any agent or IDE you already run. • where the discount comes from > They route across AMD, NVIDIA and Tenstorrent, sending each workload to the silicon that suits it. > Everyone else tunes on one kind of chip, so the saving is architectural rather than promotional. Claiming it -> Credits in the top right, pick $50, apply "UNITABETAI" at checkout. The code has been live since their June launch, so run it on your own account before you plan around it ↓

slash1s

26,238 次观看 • 6 天前

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

GLM-5.2 running on Mac Studio Clusters or RTX GPU rigs isn't how Local AI will get mass adopted. For mass adoption we need to focus on two axes: 1. Intelligence/Speed Frontier. This is being tracked on local dot ai. Aggressive co-design is needed across the entire stack to push up the frontier specifically for local hardware. Better kernels, inference tricks like spec decoding, quantizing models, model routing. 2. Usability / UX. To use Local AI today, you need to install CLIs, select a model, a quantization, a harness that works best with that model, and you need to configure your inference engine. It's not very accessible. More work needs to be done on making this seamless, so the user doesn't even know the AI is running locally.

Alex Cheema

30,607 次观看 • 1 个月前

Kimi K3 is the most powerful open-source AI model ever, and you can use it 100% free right now. Go to Sign in. Switch the dropdown from K2.6 to K3. That's it. No credit card. No API setup. On my own tests, it beat GPT 5.6 and Opus 4.8. It builds games. 3D worlds. Full websites. Even videos. It goes fully open source in July 2026. Use it off-peak hours and you get even more free tokens. Most people will never even try it. The ones who do get frontier-level AI for $0.

Kimi K3 is the most powerful open-source AI model ever, and you can use it 100% free right now. Go to Sign in. Switch the dropdown from K2.6 to K3. That's it. No credit card. No API setup. On my own tests, it beat GPT 5.6 and Opus 4.8. It builds games. 3D worlds. Full websites. Even videos. It goes fully open source in July 2026. Use it off-peak hours and you get even more free tokens. Most people will never even try it. The ones who do get frontier-level AI for $0.

Julian Goldie SEO

144,837 次观看 • 28 天前

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

girish

458,717 次观看 • 2 个月前

.Beff (e/acc) explains how thermodynamic computing fits into the current computing stack: "We don't do GPUs. They're called TSUs, thermodynamic sampling units. We think people are gonna put them next to GPUs or whatever their favorite accelerator is." "You don't need to run the whole workload on the TSU, but it could run certain parts of the workload, just like the GPU is complementary to the CPU initially." "The TSU is gonna help give you more performance per watt in your data center when combined with existing build-outs." "Let's say you're serving a large diffusion model. What we showed is that by using a TSU, you can use something called an energy-based model instead of a simple probabilistic kernel." "Overall you can have basically 100 times the performance per watt of just running on pure GPUs because our chips are much lower wattage."

.Beff (e/acc) explains how thermodynamic computing fits into the current computing stack: "We don't do GPUs. They're called TSUs, thermodynamic sampling units. We think people are gonna put them next to GPUs or whatever their favorite accelerator is." "You don't need to run the whole workload on the TSU, but it could run certain parts of the workload, just like the GPU is complementary to the CPU initially." "The TSU is gonna help give you more performance per watt in your data center when combined with existing build-outs." "Let's say you're serving a large diffusion model. What we showed is that by using a TSU, you can use something called an energy-based model instead of a simple probabilistic kernel." "Overall you can have basically 100 times the performance per watt of just running on pure GPUs because our chips are much lower wattage."

MTS

42,570 次观看 • 2 个月前

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.

Introducing EVO Router - a smart router that continuously optimizes and hill-climbs on your AI inference workloads. It learns from your code, prompts, production traffic, use cases, and SLAs, then searches for the best setup for every workload. That can mean more than choosing just a single model or routing through a classifier. EVO can optimize across model × provider combinations, fusion systems, cascades, routing policies, and prompts — whatever the workload allows, while staying within your quality, latency, and reliability constraints. As open-source models move closer to frontier-model performance, we believe this kind of workload-specific hill-climbing will become an important part of how AI systems are deployed and operated. Our early users have seen 30–60% lower inference costs across use cases ranging from complex multi-turn agents to asynchronous batch workloads. EVO Router has also reached the Pareto frontier on several benchmarks, outperforming existing setups on cost, quality, or both.

Alok Bishoyi

14,845 次观看 • 11 天前

If you use LLM-as-judge, this one is for you. (bookmark it) Most teams validate their agent's outputs by calling a frontier model as the judge. It works, until it doesn't. Three problems stack up fast: → Cost: you're hitting a frontier API on every turn, every tool call, every response. In production that burns millions. → Latency: bigger models, remote calls, slow reasoning on every check. → Blind spots: frontier models don't actually know your domain. In finance, insurance, or healthcare, they miss the keywords and principles your work depends on. So I walk through a different approach: train your own small LLM judge. Instead of a giant model, you start with a small one and let the system generate the training data for you. It decomposes your domain, samples synthetic examples, runs them through a debate arena where judges reach consensus, then trains on the refined set. The result is a judge that's cheaper, faster, and more accurate on your data than Gemini, Claude, or GPT, with an OpenAI-compatible endpoint you can even deploy on-prem. I show the whole thing end to end, using a Claude Code plugin and a web interface, with a real insurance RAG grounding evaluator as the example. You can get the plugin here: Here's the full breakdown: 00:00 - Intro 00:12 - Three problems with using frontier LLMs as judges 01:05 - A different approach: train your own small judge 01:31 - How it works (synthetic data and a debate arena) 02:50 - Installing the Claude Code plugin 04:03 - Defining your task with /eval 04:34 - Example: an insurance RAG grounding evaluator 05:51 - Kicking it off and giving early feedback 06:26 - Choosing labels, domain, and strictness 08:30 - The web interface and dashboard 09:52 - Bringing your own example data (optional) 10:26 - The finished model: endpoint, accuracy, and speed 11:16 - Control, on-prem deployment, and interpretability 11:57 - Benchmarks vs frontier models and the GitHub repo 12:30 - Outro I worked with the Plurai team on this. Thanks for sponsoring the video.

If you use LLM-as-judge, this one is for you. (bookmark it) Most teams validate their agent's outputs by calling a frontier model as the judge. It works, until it doesn't. Three problems stack up fast: → Cost: you're hitting a frontier API on every turn, every tool call, every response. In production that burns millions. → Latency: bigger models, remote calls, slow reasoning on every check. → Blind spots: frontier models don't actually know your domain. In finance, insurance, or healthcare, they miss the keywords and principles your work depends on. So I walk through a different approach: train your own small LLM judge. Instead of a giant model, you start with a small one and let the system generate the training data for you. It decomposes your domain, samples synthetic examples, runs them through a debate arena where judges reach consensus, then trains on the refined set. The result is a judge that's cheaper, faster, and more accurate on your data than Gemini, Claude, or GPT, with an OpenAI-compatible endpoint you can even deploy on-prem. I show the whole thing end to end, using a Claude Code plugin and a web interface, with a real insurance RAG grounding evaluator as the example. You can get the plugin here: Here's the full breakdown: 00:00 - Intro 00:12 - Three problems with using frontier LLMs as judges 01:05 - A different approach: train your own small judge 01:31 - How it works (synthetic data and a debate arena) 02:50 - Installing the Claude Code plugin 04:03 - Defining your task with /eval 04:34 - Example: an insurance RAG grounding evaluator 05:51 - Kicking it off and giving early feedback 06:26 - Choosing labels, domain, and strictness 08:30 - The web interface and dashboard 09:52 - Bringing your own example data (optional) 10:26 - The finished model: endpoint, accuracy, and speed 11:16 - Control, on-prem deployment, and interpretability 11:57 - Benchmarks vs frontier models and the GitHub repo 12:30 - Outro I worked with the Plurai team on this. Thanks for sponsoring the video.

Akshay 🚀

30,366 次观看 • 1 个月前

NVIDIA WILL PAY YOU $150/MONTH TO BOLT 16 BLACKWELL GPUS TO YOUR HOUSE - OR YOU BUY THE BOX AND MAKE $22,000 A YEAR same NVIDIA chips. the contract is where it gets interesting. they attach a $1,000,000 data center to your house and pay you for it - you get free internet, battery backup and cheaper electricity while they run an asset serving Amazon, Microsoft and Google 24/7 on your property or you spend $2,999 on a DGX Spark the size of a paperback - 128GB memory, runs a 70B model locally, $10/month in electricity if you were paying $1,900/month on cloud GPU rentals it pays for itself in 6 weeks and puts $22,000 back in year one one contract you are the infrastructure. the other one you own it.

NVIDIA WILL PAY YOU $150/MONTH TO BOLT 16 BLACKWELL GPUS TO YOUR HOUSE - OR YOU BUY THE BOX AND MAKE $22,000 A YEAR same NVIDIA chips. the contract is where it gets interesting. they attach a $1,000,000 data center to your house and pay you for it - you get free internet, battery backup and cheaper electricity while they run an asset serving Amazon, Microsoft and Google 24/7 on your property or you spend $2,999 on a DGX Spark the size of a paperback - 128GB memory, runs a 70B model locally, $10/month in electricity if you were paying $1,900/month on cloud GPU rentals it pays for itself in 6 weeks and puts $22,000 back in year one one contract you are the infrastructure. the other one you own it.

Sprytix

26,231 次观看 • 2 个月前

Chinese AI models are wiping billions off Big Tech right now. Google just lost $200 billion in a single day, and the model it needed to fight back still isn't ready. Gemini 3.5 Pro, Google's most powerful model, is months behind schedule. Alphabet stock dropped 4.4% that same day. The Deepseek moment is happening again, and the new model is FAR bigger. On the same day Google's delay leaked, a Beijing lab called Moonshot released Kimi K3. It is the largest open model ever built, with 2.8 trillion parameters. It took the number one spot on the Frontend Code Arena, a live coding leaderboard, passing Anthropic's best model. And Moonshot is giving it away for free on July 27. The genius part: Anyone with enough computers can download it and run a frontier level AI without paying a cent to a US company. A single task on Kimi K3 costs about 94 cents. The same work on some American models costs nearly double. So why would a company keep paying premium prices for a model it can now get for free? The entire US AI business is built on selling access to models that cost billions to train. If a free Chinese version does most of the same work, that pricing power starts to crack. And Kimi is close to the best. On one closely watched intelligence ranking it scored 57, just behind the top American models GPT-5.6 Sol and Fable 5, and ahead of Claude Opus 4.8. Bank of America told clients that Kimi proves Chinese labs can keep making big leaps even with limited chips. And the founder of Moonshot, Yang Zhilin, learned to build AI as a researcher INSIDE Google. Google literally wrote the 2017 paper that made all of these models possible. Now the people who studied its work are using it to destroy Google, and handing it out for free. What happens next: Kimi K3's weights go public on July 27. Google reports earnings on July 22, and everyone will be asking the same question about Gemini. If free models keep topping the charts, every valuation built on paid AI access has to be rewritten. What do you think?

Chinese AI models are wiping billions off Big Tech right now. Google just lost $200 billion in a single day, and the model it needed to fight back still isn't ready. Gemini 3.5 Pro, Google's most powerful model, is months behind schedule. Alphabet stock dropped 4.4% that same day. The Deepseek moment is happening again, and the new model is FAR bigger. On the same day Google's delay leaked, a Beijing lab called Moonshot released Kimi K3. It is the largest open model ever built, with 2.8 trillion parameters. It took the number one spot on the Frontend Code Arena, a live coding leaderboard, passing Anthropic's best model. And Moonshot is giving it away for free on July 27. The genius part: Anyone with enough computers can download it and run a frontier level AI without paying a cent to a US company. A single task on Kimi K3 costs about 94 cents. The same work on some American models costs nearly double. So why would a company keep paying premium prices for a model it can now get for free? The entire US AI business is built on selling access to models that cost billions to train. If a free Chinese version does most of the same work, that pricing power starts to crack. And Kimi is close to the best. On one closely watched intelligence ranking it scored 57, just behind the top American models GPT-5.6 Sol and Fable 5, and ahead of Claude Opus 4.8. Bank of America told clients that Kimi proves Chinese labs can keep making big leaps even with limited chips. And the founder of Moonshot, Yang Zhilin, learned to build AI as a researcher INSIDE Google. Google literally wrote the 2017 paper that made all of these models possible. Now the people who studied its work are using it to destroy Google, and handing it out for free. What happens next: Kimi K3's weights go public on July 27. Google reports earnings on July 22, and everyone will be asking the same question about Gemini. If free models keep topping the charts, every valuation built on paid AI access has to be rewritten. What do you think?

Ricardo

47,790 次观看 • 26 天前

A YouTuber who burns $1,000 a day on AI tokens just did the same work for $63. His terminal froze on camera from running too many agents. He force-quit and kept filming. He skipped a live event to finish this. The model is Kimi K3, China's new 2.8 trillion parameter release. Weights go public July 27. In the 41-minute breakdown he feeds it his old production codebase with a paragraph and a half of instructions. It clears 122 tasks before he touches the keyboard again. Then around minute 37 it does something to his to-do list he says he's never seen from any model. Not even Anthropic's flagship. The security audit near the 33-minute mark is the part that should worry you. Frontier models refuse that task. This one ran 25 verification agents on it. He came in bored of open weights. He left calling it frontier class. Hosting it yourself costs $2.6 million. Watching him break it costs nothing.

A YouTuber who burns $1,000 a day on AI tokens just did the same work for $63. His terminal froze on camera from running too many agents. He force-quit and kept filming. He skipped a live event to finish this. The model is Kimi K3, China's new 2.8 trillion parameter release. Weights go public July 27. In the 41-minute breakdown he feeds it his old production codebase with a paragraph and a half of instructions. It clears 122 tasks before he touches the keyboard again. Then around minute 37 it does something to his to-do list he says he's never seen from any model. Not even Anthropic's flagship. The security audit near the 33-minute mark is the part that should worry you. Frontier models refuse that task. This one ran 25 verification agents on it. He came in bored of open weights. He left calling it frontier class. Hosting it yourself costs $2.6 million. Watching him break it costs nothing.

Merlow

121,153 次观看 • 29 天前

Fireworks AI is now available first-party in Microsoft Foundry, as part of a multi-year partnership, starting today in private preview. Enterprise AI has a speed problem. Most infrastructure can't keep up with how fast open models are moving. New architectures, fine-tuned weights, models that aren't on anyone's approved list yet. The usual answer was "manage your own serving infrastructure." That's a real cost. Fireworks runs the inference. Azure owns the governance. Your weights stay yours. Beyond custom weights, teams can also access the latest open models on day zero. No waiting for the marketplace to catch up. Serverless inference for prototyping, and a path to production that doesn't require re-architecting anything. Fireworks handles the serving layer. Azure handles the rest. Your boss handles the congratulations. Want in →

Fireworks AI is now available first-party in Microsoft Foundry, as part of a multi-year partnership, starting today in private preview. Enterprise AI has a speed problem. Most infrastructure can't keep up with how fast open models are moving. New architectures, fine-tuned weights, models that aren't on anyone's approved list yet. The usual answer was "manage your own serving infrastructure." That's a real cost. Fireworks runs the inference. Azure owns the governance. Your weights stay yours. Beyond custom weights, teams can also access the latest open models on day zero. No waiting for the marketplace to catch up. Serverless inference for prototyping, and a path to production that doesn't require re-architecting anything. Fireworks handles the serving layer. Azure handles the rest. Your boss handles the congratulations. Want in →

Fireworks AI

51,657 次观看 • 5 个月前

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

savip.

68,937 次观看 • 27 天前

$NBIS cofounder Roman Chernin describes how their recent acquisitions of Eigen AI and Clarifai were all about speed, incredible talent, and acceleration: "The philosophy is very simple. We need to build so many things, and we need to move so fast, that we're always looking for people who can accelerate us. It should be exceptional talent, and/or something that has a great adoption." "Our two recent acquisitions [were] two teams that work on inference optimization. A big part of our business is how efficiently we convert GPUs into tokens. And these two teams — Eigen AI and Clarifai — one is focused on model optimization, the engine of inference. How you run specific models and all the techniques around spec decoding, quantization, and so on." "And the other is system optimization. All the routing, KV caching, and orchestration across the big cluster of compute and so on." "We have a very strong internal team working on inference. But we felt that we needed to move faster, bring more capabilities. Because the market is so fast."

$NBIS cofounder Roman Chernin describes how their recent acquisitions of Eigen AI and Clarifai were all about speed, incredible talent, and acceleration: "The philosophy is very simple. We need to build so many things, and we need to move so fast, that we're always looking for people who can accelerate us. It should be exceptional talent, and/or something that has a great adoption." "Our two recent acquisitions [were] two teams that work on inference optimization. A big part of our business is how efficiently we convert GPUs into tokens. And these two teams — Eigen AI and Clarifai — one is focused on model optimization, the engine of inference. How you run specific models and all the techniques around spec decoding, quantization, and so on." "And the other is system optimization. All the routing, KV caching, and orchestration across the big cluster of compute and so on." "We have a very strong internal team working on inference. But we felt that we needed to move faster, bring more capabilities. Because the market is so fast."

TBPN

30,608 次观看 • 3 个月前

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

FASHN AI

19,111 次观看 • 6 个月前

vLLM runs on half a million GPUs at any given moment. Most people have never heard of it. Simon Mo, co-founder and CEO of Inferact and lead maintainer of vLLM, sits down with a16z’s Matt Bornstein and Elena Burger to discuss what it takes to actually run open models in production, the advantages of open models, Simon’s mission at Inferact, and more. 00:00 Intro 01:46 When open source became critical infrastructure 08:55 Day zero model releases, and the drama behind them 14:59 What Kimi K3 actually buys you 18:56 Why open model licenses are changing 22:24 The pharmaceutical analogy for funding model training 26:16 If GPUs got 99% cheaper 29:08 Why vLLM, OpenRouter, and Ollama all started before ChatGPT 35:42 Building a company on an open source project 39:48 The inventor of RoPE removing RoPE Simon Mo Matt Bornstein Elena

vLLM runs on half a million GPUs at any given moment. Most people have never heard of it. Simon Mo, co-founder and CEO of Inferact and lead maintainer of vLLM, sits down with a16z’s Matt Bornstein and Elena Burger to discuss what it takes to actually run open models in production, the advantages of open models, Simon’s mission at Inferact, and more. 00:00 Intro 01:46 When open source became critical infrastructure 08:55 Day zero model releases, and the drama behind them 14:59 What Kimi K3 actually buys you 18:56 Why open model licenses are changing 22:24 The pharmaceutical analogy for funding model training 26:16 If GPUs got 99% cheaper 29:08 Why vLLM, OpenRouter, and Ollama all started before ChatGPT 35:42 Building a company on an open source project 39:48 The inventor of RoPE removing RoPE Simon Mo Matt Bornstein Elena

a16z

207,553 次观看 • 9 天前

Great explanation by Emad Mostaque, co-founder of Stability AI. "We’ll see the cost of Kimi K3 drop by 10 to 50 times, I think, over the next few months as it gets optimized. " Basically Kimi K3’s current inference cost is quite high, but that price reflects immature infrastructure, not a permanent technical limit. And that gap will not last long. US-based specialized infrastructure companies will optimize kernels, routing, quantization, batching, memory use, and serving systems around those models once the Kimi K3 weights are available. --- "Right now, it uses twice the number of tokens for the same task compared with GPT-5.6. Again, we’re going to see that cost drop because everyone and their dog is going to optimize the crap out of this. Fireworks has just raised funding at a $17 billion valuation, while others, such as Modal and Baseten, are valued at $10 billion. These are inference providers for open-source models. They’ve all raised around a billion dollars, which they’re now going to spend on optimizing the Chinese model, making it more efficient, and running it. American labs that handle the inference side of things are going to optimize the crap out of this. Therefore, we will see it catch up." ---- From "Peter H. Diamandis" YouTube channel, (full video link in comment)

Great explanation by Emad Mostaque, co-founder of Stability AI. "We’ll see the cost of Kimi K3 drop by 10 to 50 times, I think, over the next few months as it gets optimized. " Basically Kimi K3’s current inference cost is quite high, but that price reflects immature infrastructure, not a permanent technical limit. And that gap will not last long. US-based specialized infrastructure companies will optimize kernels, routing, quantization, batching, memory use, and serving systems around those models once the Kimi K3 weights are available. --- "Right now, it uses twice the number of tokens for the same task compared with GPT-5.6. Again, we’re going to see that cost drop because everyone and their dog is going to optimize the crap out of this. Fireworks has just raised funding at a $17 billion valuation, while others, such as Modal and Baseten, are valued at $10 billion. These are inference providers for open-source models. They’ve all raised around a billion dollars, which they’re now going to spend on optimizing the Chinese model, making it more efficient, and running it. American labs that handle the inference side of things are going to optimize the crap out of this. Therefore, we will see it catch up." ---- From "Peter H. Diamandis" YouTube channel, (full video link in comment)

Rohan Paul

82,007 次观看 • 26 天前

Palantir CEO Alex Karp explains why Europe is failing in AI: "We have a template for what doesn't work. It's called Europe." "What did Europe do? Shut everyone else out." "Our business is booming in America, and one of our brand advantages, unfortunately across the world, is Europe is trying to find ways to keep companies like Palantir out. "We see on the front line in our classified deployments where we're using open weight models, that we can get those models to be as good or better than frontier models." "What you want in a stack is an American stack that's American based—on every single part of that stack is the best part." Via FOX Business Liz Claman

Jawwwn

32,031 次观看 • 19 天前