Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Most inference clouds have moved away from custom engines toward open-source ones like vLLM and SGLang, which makes GPU capacity the real constraint. Yash Patil worked on Codex at OpenAI before co-founding Applied Compute. Building on a point from Dylan Patel he said: "If you have some GPUs and... show more

Jacob Effron

4,874 subscribers

10,021 görüntüleme • 17 gün önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 Yorum

Vantix AI Agency profil fotoğrafı

Vantix AI Agency16 gün önce

@ypatil125 @dylan522p So true when vLLM/SGLang commoditized the engine layer the moat really did shift to just securing GPU capacity

Sani Ai Tech profil fotoğrafı

Sani Ai Tech16 gün önce

@ypatil125 @dylan522p Inference is increasingly becoming a pure compute capacity game

Zara Tech & Tools profil fotoğrafı

Zara Tech & Tools16 gün önce

@ypatil125 @dylan522p Clear take on how commoditized inference has become

Amelia | AI & Tech profil fotoğrafı

Amelia | AI & Tech16 gün önce

@ypatil125 @dylan522p GPU capacity being the real constraint over engines makes total sense

Veyra | AI & Tech profil fotoğrafı

Veyra | AI & Tech16 gün önce

@ypatil125 @dylan522p GPUs plus vLLM equals production inference now

Chole Syntax Expert AI profil fotoğrafı

Chole Syntax Expert AI16 gün önce

@ypatil125 @dylan522p Spot on when everyone's on vLLM/SGLang it's all about who actually has the GPUs to serve

catman profil fotoğrafı

catman17 gün önce

@ypatil125 @dylan522p The concrete shift here is that vLLM or SGLang can turn a pool of GPUs into a production inference offering exposed through OpenRouter.

Benzer Videolar

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:

AI inference is already live on UOMI Router. Access frontier open-source models through a decentralized inference network with: • Low-cost inference • OpenAI-compatible APIs • Verifiable compute • On-chain settlement Start building: And if you have idle GPUs, there's now a second way to participate. The UOMI Provider whitelist is officially open. Instead of letting your hardware sit unused, you can contribute GPU power to the UOMI Inference Network and earn from real AI demand. Join the Provider whitelist:

Uomi

19,009 görüntüleme • 4 ay önce

🚨 YOUR GPU IS PROBABLY WASTING MORE THAN YOU THINK. vLLM is built to squeeze far more useful work out of your GPU when serving LLMs. Running an LLM at scale isn’t just about having a powerful GPU. The real problem is how efficiently you use its memory and compute. That’s where vLLM comes in. → High-throughput LLM inference and serving → PagedAttention for smarter KV-cache memory management → Continuous batching to keep GPUs busy → Prefix caching + chunked prefill → OpenAI-compatible API out of the box → Supports a huge range of modern LLM architectures → Quantization support for running models more efficiently And the crazy part? You can start an OpenAI-compatible inference server with: `vllm serve ` So your application can talk to your own model almost like it’s talking to OpenAI. The bigger idea: Don’t just buy more GPUs. Make the GPUs you already have work harder. That’s why vLLM has become such a major project in LLM inference. 🔥 #vLLM #AI #LLM #Inference #GPU #MachineLearning #AIInfrastructure #OpenSource #AIAgents #Developers

🚨 YOUR GPU IS PROBABLY WASTING MORE THAN YOU THINK. vLLM is built to squeeze far more useful work out of your GPU when serving LLMs. Running an LLM at scale isn’t just about having a powerful GPU. The real problem is how efficiently you use its memory and compute. That’s where vLLM comes in. → High-throughput LLM inference and serving → PagedAttention for smarter KV-cache memory management → Continuous batching to keep GPUs busy → Prefix caching + chunked prefill → OpenAI-compatible API out of the box → Supports a huge range of modern LLM architectures → Quantization support for running models more efficiently And the crazy part? You can start an OpenAI-compatible inference server with: `vllm serve ` So your application can talk to your own model almost like it’s talking to OpenAI. The bigger idea: Don’t just buy more GPUs. Make the GPUs you already have work harder. That’s why vLLM has become such a major project in LLM inference. 🔥 #vLLM #AI #LLM #Inference #GPU #MachineLearning #AIInfrastructure #OpenSource #AIAgents #Developers

Vikas gupta

14,138 görüntüleme • 1 ay önce

Today we announced a $150M seed round in Inferact, a new startup led by the maintainers of the vLLM project. Inferact will support the vLLM open source project through dedicated financial and developer resources and build what they see as the next generation commercial inference engine. Cofounders Simon Mo and Woosuk Kwon joined a16z GP Matt Bornstein for a conversation on how vLLM came to be, what they’ve learned from building it, and what they’re now doing at Inferact. They cover how vLLM began as a side project, why open source is essential to the world’s AI infrastructure, why inference is getting harder, and more. 00:00 Introduction 11:41 Community and collaboration in vLLM 19:19 Understanding inference engines 24:27 Cluster scale and GPU deployment 31:19 Belief in open source AI 35:45 Founding Inferact 40:00 The future of Inference at scale Simon Mo Woosuk Kwon Matt Bornstein

Today we announced a $150M seed round in Inferact, a new startup led by the maintainers of the vLLM project. Inferact will support the vLLM open source project through dedicated financial and developer resources and build what they see as the next generation commercial inference engine. Cofounders Simon Mo and Woosuk Kwon joined a16z GP Matt Bornstein for a conversation on how vLLM came to be, what they’ve learned from building it, and what they’re now doing at Inferact. They cover how vLLM began as a side project, why open source is essential to the world’s AI infrastructure, why inference is getting harder, and more. 00:00 Introduction 11:41 Community and collaboration in vLLM 19:19 Understanding inference engines 24:27 Cluster scale and GPU deployment 31:19 Belief in open source AI 35:45 Founding Inferact 40:00 The future of Inference at scale Simon Mo Woosuk Kwon Matt Bornstein

a16z

88,839 görüntüleme • 9 ay önce

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

211,070 görüntüleme • 2 ay önce

Already running an inference engine? So where does NVIDIA Dynamo fit in? In five minutes, we break down how Dynamo sits around engines like SGLang, vLLM and TensorRT-LLM to scale inference across GPUs and nodes. Full video in the comments 🔽

Already running an inference engine? So where does NVIDIA Dynamo fit in? In five minutes, we break down how Dynamo sits around engines like SGLang, vLLM and TensorRT-LLM to scale inference across GPUs and nodes. Full video in the comments 🔽

NVIDIA AI

30,908 görüntüleme • 1 ay önce

In 2022, Berkeley PhD student Woosuk Kwon thought he could make Meta's new open-weight model, OPT-175B, run faster in two weeks. Four years and 3,000 contributors later, that project is vLLM, one of the largest open-source inference engines, running on ~500,000 GPUs at any given time. He and fellow researchers Simon Mo, Kaichao You, and Roger Wang borrowed "virtual memory" from operating systems, handing out memory only as it's needed so each GPU can juggle requests of wildly different sizes. (The "v" in vLLM is for virtual.) Their first user, Berkeley neighbor Arena.ai, cut its GPU needs in half. Today Google, Amazon, and Meta all run vLLM in production. In January, the core maintainers founded Inferact and raised $150M to give vLLM a full-time team. They're hiring across eng, marketing, and devrel in SF and Singapore: Simon Mo Woosuk Kwon Kaichao You Roger Wang

In 2022, Berkeley PhD student Woosuk Kwon thought he could make Meta's new open-weight model, OPT-175B, run faster in two weeks. Four years and 3,000 contributors later, that project is vLLM, one of the largest open-source inference engines, running on ~500,000 GPUs at any given time. He and fellow researchers Simon Mo, Kaichao You, and Roger Wang borrowed "virtual memory" from operating systems, handing out memory only as it's needed so each GPU can juggle requests of wildly different sizes. (The "v" in vLLM is for virtual.) Their first user, Berkeley neighbor Arena.ai, cut its GPU needs in half. Today Google, Amazon, and Meta all run vLLM in production. In January, the core maintainers founded Inferact and raised $150M to give vLLM a full-time team. They're hiring across eng, marketing, and devrel in SF and Singapore: Simon Mo Woosuk Kwon Kaichao You Roger Wang

a16z

70,829 görüntüleme • 8 gün önce

Dylan Patel on the importance of memory and storage Two key quotes: "An $NVDA GPU is faster than an $AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads." “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly" Full Quote: “We have over $80 million of compute: GPUs from $NVDA and $AMD, TPUs from Google, and Trainium from Amazon. We constantly run this benchmark using the newest inference engines, drivers, PyTorch versions, and other software. It runs every day through automated CI across the latest Chinese models from GLM, Zhipu, Moonshot, Kimi, Alibaba, and others. Initially, when we were benchmarking the differences between these chips, inference engines, and parallelism schemes, we used fixed context lengths. But with Agent X, we have now analyzed more than $5 million worth of Claude Code traces. This is real production traffic that users have donated to us, combined with internally generated data, so we now understand what an actual agent workload looks like. When we implement those workloads and run the benchmarks, it turns out that the chip you are using is very important, but how you handle memory offload can be even more important. An Nvidia GPU is faster than an AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads. Similarly, you can use a less powerful GPU with a much better storage solution and outperform the best GPU when it lacks those solutions. Simply buying the newest GPU does not necessarily give you the best inference economics. You need to layer in other innovations, including storage and memory.” Interviewer: “Who is the top player on your chart? Can you tell us?” Dylan Patel: “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly.”

Dylan Patel on the importance of memory and storage Two key quotes: "An $NVDA GPU is faster than an $AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads." “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly" Full Quote: “We have over $80 million of compute: GPUs from $NVDA and $AMD, TPUs from Google, and Trainium from Amazon. We constantly run this benchmark using the newest inference engines, drivers, PyTorch versions, and other software. It runs every day through automated CI across the latest Chinese models from GLM, Zhipu, Moonshot, Kimi, Alibaba, and others. Initially, when we were benchmarking the differences between these chips, inference engines, and parallelism schemes, we used fixed context lengths. But with Agent X, we have now analyzed more than $5 million worth of Claude Code traces. This is real production traffic that users have donated to us, combined with internally generated data, so we now understand what an actual agent workload looks like. When we implement those workloads and run the benchmarks, it turns out that the chip you are using is very important, but how you handle memory offload can be even more important. An Nvidia GPU is faster than an AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads. Similarly, you can use a less powerful GPU with a much better storage solution and outperform the best GPU when it lacks those solutions. Simply buying the newest GPU does not necessarily give you the best inference economics. You need to layer in other innovations, including storage and memory.” Interviewer: “Who is the top player on your chart? Can you tell us?” Dylan Patel: “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly.”

Daniel Romero

48,978 görüntüleme • 3 ay önce

When Christopher Nolan promoted the Oppenheimer (2023) Blu-ray and 4K release, he said: “We worked hard on this so you have a version to buy and own. Put it on the shelf so no evil streaming service can come steal it from you.”

When Christopher Nolan promoted the Oppenheimer (2023) Blu-ray and 4K release, he said: “We worked hard on this so you have a version to buy and own. Put it on the shelf so no evil streaming service can come steal it from you.”

cinesthetic.

1,886,003 görüntüleme • 3 ay önce

Dylan Patel of SemiAnalysis says a worse GPU with better storage and memory now beats the best chip without them, so buying the newest GPU alone no longer wins inference. So, an AMD GPU with more memory can outperform Nvidia in some cases. "So what we have is we have over $80 million of compute, GPUs from Nvidia, AMD, TPUs from Google, Trainium from Amazon, and we run this benchmark constantly on the newest inference engine, newest drivers, newest PyTorch version, whatever it is." "Every day it runs on an automated CI, and we run it on all the latest Chinese models, from GLM, Zhipu, Moonshot, Kimi, Alibaba, all these models we run." "Initially, when we were benchmarking the difference between these chips and different engines, different schemes for parallelism, we were just running it fixed context length." "But now with Agent X, we've analyzed over $5 million worth of Claude Code traces. This is real production traffic that people have donated to us as well as internally generated. Now we know what the actual agent workload looks like." "And then as we implement that and run those benchmarks, it turns out yes, the chip you're using is very important, but now even more important is how are you handling this memory offload?" "And so while an Nvidia GPU is faster than an AMD GPU in most cases, because AMD GPUs have more memory, they actually end up outperforming in some cases." "Or you can have a worse GPU, but a much better storage solution, and now you can outperform what the best GPU can do without those solutions. So just buying the newest and latest GPU alone doesn't get you the best inference economics." "Actually, you need to layer in all these other innovations including storage and memory." [ Who's the top player on your chart? ] "That really is a difficult multivariable problem. And generally that means you need to have, yes, you need to have the best GPU, a GB300, but you also need to have the best storage solutions. And so I won't spoil who's the best right here, but I will say that storage solutions matter a lot and memory solutions matter a lot, as does your front-end networking. That matters a lot."

Dylan Patel of SemiAnalysis says a worse GPU with better storage and memory now beats the best chip without them, so buying the newest GPU alone no longer wins inference. So, an AMD GPU with more memory can outperform Nvidia in some cases. "So what we have is we have over $80 million of compute, GPUs from Nvidia, AMD, TPUs from Google, Trainium from Amazon, and we run this benchmark constantly on the newest inference engine, newest drivers, newest PyTorch version, whatever it is." "Every day it runs on an automated CI, and we run it on all the latest Chinese models, from GLM, Zhipu, Moonshot, Kimi, Alibaba, all these models we run." "Initially, when we were benchmarking the difference between these chips and different engines, different schemes for parallelism, we were just running it fixed context length." "But now with Agent X, we've analyzed over $5 million worth of Claude Code traces. This is real production traffic that people have donated to us as well as internally generated. Now we know what the actual agent workload looks like." "And then as we implement that and run those benchmarks, it turns out yes, the chip you're using is very important, but now even more important is how are you handling this memory offload?" "And so while an Nvidia GPU is faster than an AMD GPU in most cases, because AMD GPUs have more memory, they actually end up outperforming in some cases." "Or you can have a worse GPU, but a much better storage solution, and now you can outperform what the best GPU can do without those solutions. So just buying the newest and latest GPU alone doesn't get you the best inference economics." "Actually, you need to layer in all these other innovations including storage and memory." [ Who's the top player on your chart? ] "That really is a difficult multivariable problem. And generally that means you need to have, yes, you need to have the best GPU, a GB300, but you also need to have the best storage solutions. And so I won't spoil who's the best right here, but I will say that storage solutions matter a lot and memory solutions matter a lot, as does your front-end networking. That matters a lot."

Fireside Alpha

185,279 görüntüleme • 3 ay önce

Everything in Kingmakers is real. If you see a building, you can go inside it, have a fight in it, and blow it up. If you die in Kingmakers, you die in real life. Please wishlist on Steam!

Everything in Kingmakers is real. If you see a building, you can go inside it, have a fight in it, and blow it up. If you die in Kingmakers, you die in real life. Please wishlist on Steam!

Kingmakers Game

3,958,549 görüntüleme • 2 yıl önce

CMU PhD who built the kernels NVIDIA now ships in TensorRT-LLM explained fast attention in 68 minutes - better than $1200 GPU programming courses. pick the attention pattern -> generate a fused CUDA kernel -> drop it into vLLM/SGLang -> same GPU, way more tokens per second. That loop is why FlashInfer now powers inference at NVIDIA, vLLM, SGLang, and half the serving stacks you use. FlashInfer + Triton + JIT-compiled kernels + paged-KV attention - that's the stack.

CMU PhD who built the kernels NVIDIA now ships in TensorRT-LLM explained fast attention in 68 minutes - better than $1200 GPU programming courses. pick the attention pattern -> generate a fused CUDA kernel -> drop it into vLLM/SGLang -> same GPU, way more tokens per second. That loop is why FlashInfer now powers inference at NVIDIA, vLLM, SGLang, and half the serving stacks you use. FlashInfer + Triton + JIT-compiled kernels + paged-KV attention - that's the stack.

h100envy

32,605 görüntüleme • 3 ay önce

Ying Sheng co-wrote SGLang, the inference engine now serving Grok at xAI on a hundred thousand GPUs. She also built FlexGen, which made a 175-billion model run on a single consumer GPU, and helped build Chatbot Arena. Three artifacts the whole field uses, one researcher. SGLang hit a 5x cost cut over DeepSeek's own API, and a dozen teams reproduced it. Everyone argues about models. She builds the engines that actually serve them cheaply enough to survive.

Ying Sheng co-wrote SGLang, the inference engine now serving Grok at xAI on a hundred thousand GPUs. She also built FlexGen, which made a 175-billion model run on a single consumer GPU, and helped build Chatbot Arena. Three artifacts the whole field uses, one researcher. SGLang hit a 5x cost cut over DeepSeek's own API, and a dozen teams reproduced it. Everyone argues about models. She builds the engines that actually serve them cheaply enough to survive.

h100envy

40,959 görüntüleme • 4 ay önce

📢 Inference is ON 😎 Run any AI model on dedicated GPU hardware, starting today. The GPU is yours while you're on it, the full price is displayed before you commit, and the model is whatever you bring from Hugging Face. Wild concept, we know! 👇

📢 Inference is ON 😎 Run any AI model on dedicated GPU hardware, starting today. The GPU is yours while you're on it, the full price is displayed before you commit, and the model is whatever you bring from Hugging Face. Wild concept, we know! 👇

Ocean Network

459,195 görüntüleme • 1 ay önce

Trump: 100% tariff on all chips and semiconductors coming into the United States.. if you have made a commitment to build or are in the process of building, as many are, there is no tariff. Ok? If for some reason, you say you are building and you don't build, then we add it up, it accumulates, and we charge you at a later date, you have to pay, and that is a guarantee

Trump: 100% tariff on all chips and semiconductors coming into the United States.. if you have made a commitment to build or are in the process of building, as many are, there is no tariff. Ok? If for some reason, you say you are building and you don't build, then we add it up, it accumulates, and we charge you at a later date, you have to pay, and that is a guarantee

Acyn

179,998 görüntüleme • 1 yıl önce

ALERT🚨 GB300 NVL72 NVLINK BACKPLANE ENABLES 13x BETTER PERF PER DOLLAR THAN HOPPER ON AGENTIC INFERENCE Through extreme co-design, GB300 NVL72 uses an innovative copper backplane to expand the scale-up domain to 72 versus 8 on Hopper. This allows optimizations like vLLM wide expert parallelism, which allows each GPU to have only a subset of experts.

ALERT🚨 GB300 NVL72 NVLINK BACKPLANE ENABLES 13x BETTER PERF PER DOLLAR THAN HOPPER ON AGENTIC INFERENCE Through extreme co-design, GB300 NVL72 uses an innovative copper backplane to expand the scale-up domain to 72 versus 8 on Hopper. This allows optimizations like vLLM wide expert parallelism, which allows each GPU to have only a subset of experts.

SemiAnalysis

62,886 görüntüleme • 1 ay önce

Jensen spent 2 min on InferenceMAX at the GTC keynote 😎 InferenceMAX is completely open source and completely impartial, with the support of AMD, OpenAI, Nvidia, Microsoft, Oracle, Pytorch, SGLang, vLLM, Cursoe, Nebius, Tensorwave, etc

Jensen spent 2 min on InferenceMAX at the GTC keynote 😎 InferenceMAX is completely open source and completely impartial, with the support of AMD, OpenAI, Nvidia, Microsoft, Oracle, Pytorch, SGLang, vLLM, Cursoe, Nebius, Tensorwave, etc

Dylan Patel

87,986 görüntüleme • 1 yıl önce

We co-led Inferact's $150M seed round to support them in their mission to build the inference engine for all current and future AI. In this episode of The Investment Memo, Lightspeed's Bucky Moore and James Alcorn sit down with Simon Mo (Co-Founder & CEO Inferact) to cover: - How vLLM grew to 60K+ GitHub stars - Why inference is shifting to the majority of compute - How vLLM evolved from a research project into the industry standard - Why building a company was the next step to push open-source inference forward 00:00 Introduction 02:03 The investment memo 04:47 Latency vs throughput vs cost 06:19 Paged attention explained 08:04 The evolution of attention 09:42 Growing the vLLM open source community 11:41 Working with hardware vendors 14:45 Deploying vLLM at large scale 16:03 Inferact's culture of openness 18:45 Building an open ecosystem and horizontal stack 19:45 Inferact's approach to fundraising 22:14 What is the future of inference? Simon Mo Bucky Moore James Alcorn

We co-led Inferact's $150M seed round to support them in their mission to build the inference engine for all current and future AI. In this episode of The Investment Memo, Lightspeed's Bucky Moore and James Alcorn sit down with Simon Mo (Co-Founder & CEO Inferact) to cover: - How vLLM grew to 60K+ GitHub stars - Why inference is shifting to the majority of compute - How vLLM evolved from a research project into the industry standard - Why building a company was the next step to push open-source inference forward 00:00 Introduction 02:03 The investment memo 04:47 Latency vs throughput vs cost 06:19 Paged attention explained 08:04 The evolution of attention 09:42 Growing the vLLM open source community 11:41 Working with hardware vendors 14:45 Deploying vLLM at large scale 16:03 Inferact's culture of openness 18:45 Building an open ecosystem and horizontal stack 19:45 Inferact's approach to fundraising 22:14 What is the future of inference? Simon Mo Bucky Moore James Alcorn

Lightspeed

27,040 görüntüleme • 9 ay önce

AI agents have full root access to your computer. In the '90s we called that a virus and installed McAfee to stop it. "Run it on a totally different computer, one that is locked away from everything. If you put it on your home network, you might have a bad time." - Marks

AI agents have full root access to your computer. In the '90s we called that a virus and installed McAfee to stop it. "Run it on a totally different computer, one that is locked away from everything. If you put it on your home network, you might have a bad time." - Marks

TFTC

17,278 görüntüleme • 7 ay önce

you can create complex agentic environments and launch RL training runs with a single prompt. deploy trained inference endpoints with a single click. no GPUs, no SSH, no vLLM. just `prime`. guide:

you can create complex agentic environments and launch RL training runs with a single prompt. deploy trained inference endpoints with a single click. no GPUs, no SSH, no vLLM. just `prime`. guide:

will brown

139,747 görüntüleme • 7 ay önce