Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

336,601 subscribers

29,221 views • 4 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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 views • 2 months ago

AI that responds in under 100ms doesn't happen by accident. Together AI VP of Kernels Dan Fu shares how they use NVIDIA CUDA, TensorRT-LLM, Dynamo and Together ATLAS on NVIDIA Blackwell to power ultra-low-latency inference and long context code generation for Cursor. From building megakernels that fuse an entire model's forward pass into a single launch to enabling real-time voice agents, Together AI is optimizing latency at every layer of the stack.

AI that responds in under 100ms doesn't happen by accident. Together AI VP of Kernels Dan Fu shares how they use NVIDIA CUDA, TensorRT-LLM, Dynamo and Together ATLAS on NVIDIA Blackwell to power ultra-low-latency inference and long context code generation for Cursor. From building megakernels that fuse an entire model's forward pass into a single launch to enabling real-time voice agents, Together AI is optimizing latency at every layer of the stack.

NVIDIA AI Infrastructure

20,633 views • 2 months ago

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

87,993 views • 7 months ago

"The inflection point for inference has arrived." — Jensen Huang, Founder & CEO of NVIDIA We’ve officially crossed a new milestone in the inference era — where widespread adoption of AI shifts from learning to doing. The breakthrough: extreme codesign across hardware and software driving down cost per token. Lower cost → more inference More inference → more users and applications More users and applications → exponential AI revenue growth

"The inflection point for inference has arrived." — Jensen Huang, Founder & CEO of NVIDIA We’ve officially crossed a new milestone in the inference era — where widespread adoption of AI shifts from learning to doing. The breakthrough: extreme codesign across hardware and software driving down cost per token. Lower cost → more inference More inference → more users and applications More users and applications → exponential AI revenue growth

NVIDIA

82,009 views • 5 months ago

New course: Efficient Inference with SGLang: Text and Image Generation, built in partnership with LMSys LMSYS Org and RadixArk RadixArk, and taught by Richard Chen Richard Chen, a Member of Technical Staff at RadixArk. Running LLMs in production is expensive, and much of that cost comes from redundant computation. This short course teaches you to eliminate that waste using SGLang, an open-source inference framework that caches computation already done and reuses it across future requests. When ten users share the same system prompt, SGLang processes it once, not ten times. The speedups compound quickly, especially when there's a lot of shared context across requests. Skills you'll gain: - Implement a KV cache from scratch to eliminate redundant computation within a single request - Scale caching across users and requests with RadixAttention, so shared context is only processed once - Accelerate image generation with diffusion models using SGLang's caching and multi-GPU parallelism Join and learn to make LLM inference faster and more cost-efficient at scale!

New course: Efficient Inference with SGLang: Text and Image Generation, built in partnership with LMSys LMSYS Org and RadixArk RadixArk, and taught by Richard Chen Richard Chen, a Member of Technical Staff at RadixArk. Running LLMs in production is expensive, and much of that cost comes from redundant computation. This short course teaches you to eliminate that waste using SGLang, an open-source inference framework that caches computation already done and reuses it across future requests. When ten users share the same system prompt, SGLang processes it once, not ten times. The speedups compound quickly, especially when there's a lot of shared context across requests. Skills you'll gain: - Implement a KV cache from scratch to eliminate redundant computation within a single request - Scale caching across users and requests with RadixAttention, so shared context is only processed once - Accelerate image generation with diffusion models using SGLang's caching and multi-GPU parallelism Join and learn to make LLM inference faster and more cost-efficient at scale!

Andrew Ng

101,794 views • 4 months ago

Fully local Code Assistant running on NVIDIA GPU! In this tutorial, I'll show you how to run Llama3 using TensorRT and Nvidia's Triton Inference Server to use it as a Code Assistant in VSCode In this thread 🧵, I'll walk you through the integration process, explaining each step simply and clearly 👇 NVIDIA AI NVIDIA AIDev AI at Meta

Fully local Code Assistant running on NVIDIA GPU! In this tutorial, I'll show you how to run Llama3 using TensorRT and Nvidia's Triton Inference Server to use it as a Code Assistant in VSCode In this thread 🧵, I'll walk you through the integration process, explaining each step simply and clearly 👇 NVIDIA AI NVIDIA AIDev AI at Meta

Daniel San

42,154 views • 2 years ago

Ex-vLLM core contributor explained how to make LLM inference 10x cheaper in 34 minutes - better than $3000 inference optimization bootcamps. request comes in -> check LMCache -> hit? load KV cache from CPU/SSD/remote -> skip prefill -> serve. That loop is why Bloomberg and other production stacks now push 300 terabytes of KV cache per week. LMCache + vLLM + CPU/SSD/remote storage + zero-copy CUDA kernels - that's the stack. Watch and save it, then wire the KV-offload into your inference stack.

Ex-vLLM core contributor explained how to make LLM inference 10x cheaper in 34 minutes - better than $3000 inference optimization bootcamps. request comes in -> check LMCache -> hit? load KV cache from CPU/SSD/remote -> skip prefill -> serve. That loop is why Bloomberg and other production stacks now push 300 terabytes of KV cache per week. LMCache + vLLM + CPU/SSD/remote storage + zero-copy CUDA kernels - that's the stack. Watch and save it, then wire the KV-offload into your inference stack.

h100envy

61,430 views • 1 month ago

Ex-Berkeley PhD who leads SGLang at xAI explained how they serve Grok on 100K GPUs in 23 minutes - better than $2000 inference-at-scale courses. split prefill and decode -> shard experts across GPUs -> route tokens per expert -> overlap comm and compute -> serve at DeepSeek-API-killing prices. That loop is why xAI runs Grok on SGLang and third parties beat DeepSeek's own API by 5x on cost. SGLang + prefill-decode disaggregation + expert parallelism + AMD MI300 - that's the stack. Watch and save it, then read the article below.

Ex-Berkeley PhD who leads SGLang at xAI explained how they serve Grok on 100K GPUs in 23 minutes - better than $2000 inference-at-scale courses. split prefill and decode -> shard experts across GPUs -> route tokens per expert -> overlap comm and compute -> serve at DeepSeek-API-killing prices. That loop is why xAI runs Grok on SGLang and third parties beat DeepSeek's own API by 5x on cost. SGLang + prefill-decode disaggregation + expert parallelism + AMD MI300 - that's the stack. Watch and save it, then read the article below.

h100envy

319,581 views • 1 month ago

NVIDIA Vera Rubin is in full production and arrives just in time for the next frontier of AI. The #NVIDIARubin platform uses extreme co-design across six new chips to accelerate agentic AI, advanced reasoning and massive-scale MoE model inference. NVIDIA Vera Rubin NVL72: Six new chips, one AI supercomputer — see how we built it.

NVIDIA Vera Rubin is in full production and arrives just in time for the next frontier of AI. The #NVIDIARubin platform uses extreme co-design across six new chips to accelerate agentic AI, advanced reasoning and massive-scale MoE model inference. NVIDIA Vera Rubin NVL72: Six new chips, one AI supercomputer — see how we built it.

NVIDIA Data Center

27,643 views • 7 months ago

📣 CoreWeave and NVIDIA are accelerating the build out of AI factories—token generators that directly drive revenue. This includes adoption of and support for: ✅ NVIDIA Vera Rubin deployment, starting in 2H 2026 ✅ NVIDIA Vera CPU and BlueField-4 STX ✅ NVIDIA Dynamo for inference and NVIDIA Agent Toolkit and OpenShell for long-running agents ✅ NVIDIA DSX Air for digital twins of AI factories Learn more ➡️

📣 CoreWeave and NVIDIA are accelerating the build out of AI factories—token generators that directly drive revenue. This includes adoption of and support for: ✅ NVIDIA Vera Rubin deployment, starting in 2H 2026 ✅ NVIDIA Vera CPU and BlueField-4 STX ✅ NVIDIA Dynamo for inference and NVIDIA Agent Toolkit and OpenShell for long-running agents ✅ NVIDIA DSX Air for digital twins of AI factories Learn more ➡️

NVIDIA AI Infrastructure

10,213 views • 4 months ago

in the lectures below, i hold your hand through low-level LLM systems engineering. it includes everything up to TODAY! 1) pytorch tensors 2) large matmul on cpu vs gpu 3) JAX (and why xAI uses it instead of pytorch) 4) raw cuda kernels and global threading indexing 5) triton design philosophy and softmax example 6) HIP kernels 7) mapping out the ENTIRE ecosystem + differences between CUDA and ROCm/HIP (BLAS, FFT, DNN) 8) cutlass and cute-dsl 9) pretraining, finetuning, rl, unsloth, axolotl, megatron-lm, deepspeed, nanogpt, nanochat 10) training vs inference, inference serving problems, throughput vs latency vs concurrency scaling, vllm, sglang, tensorrt-llm, tensorrt, llama.cpp, exllamav2, exllamav3, benchmark comparisons 11) projects/companies using llms to generate SOTA cuda/triton kernels 12) luminal inference 13) mojo/modular/max

in the lectures below, i hold your hand through low-level LLM systems engineering. it includes everything up to TODAY! 1) pytorch tensors 2) large matmul on cpu vs gpu 3) JAX (and why xAI uses it instead of pytorch) 4) raw cuda kernels and global threading indexing 5) triton design philosophy and softmax example 6) HIP kernels 7) mapping out the ENTIRE ecosystem + differences between CUDA and ROCm/HIP (BLAS, FFT, DNN) 8) cutlass and cute-dsl 9) pretraining, finetuning, rl, unsloth, axolotl, megatron-lm, deepspeed, nanogpt, nanochat 10) training vs inference, inference serving problems, throughput vs latency vs concurrency scaling, vllm, sglang, tensorrt-llm, tensorrt, llama.cpp, exllamav2, exllamav3, benchmark comparisons 11) projects/companies using llms to generate SOTA cuda/triton kernels 12) luminal inference 13) mojo/modular/max

Elliot Arledge

58,323 views • 10 months ago

Among the fastest DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B inference in the market, per Artificial Analysis benchmarks (April 2026). ⚡️🤖 Sub-1-second TTFT. 230 tokens per second. Co-designed every layer of the stack with Inferact, performance optimized vLLM, all on NVIDIA HGX B300. Live on DigitalOcean Serverless Inference now. Full breakdown in the comments. ⬇️

Among the fastest DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B inference in the market, per Artificial Analysis benchmarks (April 2026). ⚡️🤖 Sub-1-second TTFT. 230 tokens per second. Co-designed every layer of the stack with Inferact, performance optimized vLLM, all on NVIDIA HGX B300. Live on DigitalOcean Serverless Inference now. Full breakdown in the comments. ⬇️

DigitalOcean

39,063 views • 4 months ago

Laguna S 2.1 is built to run locally. We heard the ask for a serious open model in the 80–120B range. Laguna S 2.1 is our answer, and we want it to redefine what this size class can do. Weights ship in BF16, FP8, INT4 and NVFP4, with official GGUF and MLX conversions, plus official DFlash draft models for faster inference. Day-one support across llama.cpp, ollama, Valerie Lee Make Up, SGLang, NVIDIA TRT-LLM, Hugging Face transformers and ZML. Watch it run on an NVIDIA AI DGX Spark.

Laguna S 2.1 is built to run locally. We heard the ask for a serious open model in the 80–120B range. Laguna S 2.1 is our answer, and we want it to redefine what this size class can do. Weights ship in BF16, FP8, INT4 and NVFP4, with official GGUF and MLX conversions, plus official DFlash draft models for faster inference. Day-one support across llama.cpp, ollama, Valerie Lee Make Up, SGLang, NVIDIA TRT-LLM, Hugging Face transformers and ZML. Watch it run on an NVIDIA AI DGX Spark.

Poolside

31,242 views • 1 month ago

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 views • 7 months ago

"Inference, if you look at it as a market, will be much, much bigger than cloud computing was pre-ChatGPT." Lightspeed’s Bucky Moore says inference is an underrated investment category in AI, and expects the market to break up into large, specialized platforms for each modality: "The GPU supply crunch that we're seeing right now is largely, as Dylan Patel has said on the show before, due to the fact that not only these consumer products, but also B2B products like Claude Code and Codex are just really taking off and creating insane demand for inference." "We're talking hundreds of billions in spend every year. And if that's true, I think there will be very, very large inference platforms built in each modality." "So there will be an inference platform for real-time video models, there will be an inference platform for open-source and custom language models, there will be an inference platform built specifically for long-running agents." "So I think we're just going to see that industry, which today looks like one industry, break up into many because of how big it is and how much room for specialization there is."

"Inference, if you look at it as a market, will be much, much bigger than cloud computing was pre-ChatGPT." Lightspeed’s Bucky Moore says inference is an underrated investment category in AI, and expects the market to break up into large, specialized platforms for each modality: "The GPU supply crunch that we're seeing right now is largely, as Dylan Patel has said on the show before, due to the fact that not only these consumer products, but also B2B products like Claude Code and Codex are just really taking off and creating insane demand for inference." "We're talking hundreds of billions in spend every year. And if that's true, I think there will be very, very large inference platforms built in each modality." "So there will be an inference platform for real-time video models, there will be an inference platform for open-source and custom language models, there will be an inference platform built specifically for long-running agents." "So I think we're just going to see that industry, which today looks like one industry, break up into many because of how big it is and how much room for specialization there is."

TBPN

33,278 views • 5 months ago

🤝 Arcee.ai, an American AI lab, built its frontier open model family on NVIDIA Blackwell Ultra. Its flagship MoE model, Trinity-Large-Thinking, was RL post-trained using NVIDIA NeMo open libraries. Arcee optimized agentic model inference with NVIDIA Dynamo and vLLM, along with NVIDIA accelerated networking, to deliver low token cost, achieving: ✅ 3T+ tokens served on OpenRouter in its first two months ✅ $0.90 per 1M output tokens ✅ 2nd on PinchBench for open agentic models Explore Arcee's open models, powered by NVIDIA ➡️

🤝 Arcee.ai, an American AI lab, built its frontier open model family on NVIDIA Blackwell Ultra. Its flagship MoE model, Trinity-Large-Thinking, was RL post-trained using NVIDIA NeMo open libraries. Arcee optimized agentic model inference with NVIDIA Dynamo and vLLM, along with NVIDIA accelerated networking, to deliver low token cost, achieving: ✅ 3T+ tokens served on OpenRouter in its first two months ✅ $0.90 per 1M output tokens ✅ 2nd on PinchBench for open agentic models Explore Arcee's open models, powered by NVIDIA ➡️

NVIDIA AI Infrastructure

27,377 views • 1 month ago

Lightchain AI – Decentralized Inference Demo 🍂🥧 + Blockchain Rewards In this video, we showcase how Lightchain AI’s decentralized inference engine (AIVM + PoI + Federated Learning) runs a real-world prompt “What is the best way to make pumpkin pie for thanksgiving dinner?” 💰 Blockchain Rewards in Action This demo doesn’t just show inference — it shows how inference providers are rewarded for their work. The provider that processed this prompt was automatically rewarded on the Lightchain testnet. 🍁 Why It Matters Unlike centralized AI, Lightchain AI distributes inference across a global network of participants. Nodes earn blockchain rewards for providing compute, ensuring a trustless, transparent, and economically sustainable ecosystem. With pay-to-prompt mechanics and DAO governance, Lightchain AI creates a fair AI economy for all. 🌐 Learn more at-

Lightchain AI – Decentralized Inference Demo 🍂🥧 + Blockchain Rewards In this video, we showcase how Lightchain AI’s decentralized inference engine (AIVM + PoI + Federated Learning) runs a real-world prompt “What is the best way to make pumpkin pie for thanksgiving dinner?” 💰 Blockchain Rewards in Action This demo doesn’t just show inference — it shows how inference providers are rewarded for their work. The provider that processed this prompt was automatically rewarded on the Lightchain testnet. 🍁 Why It Matters Unlike centralized AI, Lightchain AI distributes inference across a global network of participants. Nodes earn blockchain rewards for providing compute, ensuring a trustless, transparent, and economically sustainable ecosystem. With pay-to-prompt mechanics and DAO governance, Lightchain AI creates a fair AI economy for all. 🌐 Learn more at-

Lightchain AI

18,665 views • 1 year ago

What is AI inference engineering, why is it such an in-demand skill, and how do you break into the field? With author of Inference Engineering Philip Kiely and head of training at Baseten Charlie O'Neill 0:00: What is inference? 2:47: History of inference 4:59: Downstream effects of AI research on inference 13:54: What you'll learn from Inference Engineering 16:14: Advice for engineers transitioning into AI 19:00: Open source models driving inference growth 20:55: Specialization vs. frontier closed models 23:51: "Big Token" and the importance of open source AI 27:18: Where to get Inference Engineering

What is AI inference engineering, why is it such an in-demand skill, and how do you break into the field? With author of Inference Engineering Philip Kiely and head of training at Baseten Charlie O'Neill 0:00: What is inference? 2:47: History of inference 4:59: Downstream effects of AI research on inference 13:54: What you'll learn from Inference Engineering 16:14: Advice for engineers transitioning into AI 19:00: Open source models driving inference growth 20:55: Specialization vs. frontier closed models 23:51: "Big Token" and the importance of open source AI 27:18: Where to get Inference Engineering

Madison Kanna

119,268 views • 5 months ago

Pods, nodes, control planes... confused? 🤔 We break down Kubernetes 101 and how GKE simplifies container management in less than 60 seconds. Learn how to scale your apps without the complexity. Get started →

Pods, nodes, control planes... confused? 🤔 We break down Kubernetes 101 and how GKE simplifies container management in less than 60 seconds. Learn how to scale your apps without the complexity. Get started →

Google Cloud Tech

10,199 views • 6 months ago