Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

PyTorch core engineer at Meta turned CUDA kernel writing into a sport in 13 minutes - better than $1500 GPU programming bootcamps. profile the kernel -> find the bottleneck -> rewrite -> benchmark -> merge the winning code into PyTorch. That loop is how the open community now beats...

h100envy's profile picture

h100envy

1,125 subscribers

35,148 Aufrufe • vor 4 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Introducing The AI CUDA Engineer: An agentic AI system that automates the production of highly optimized CUDA kernels. The AI CUDA Engineer can produce highly optimized CUDA kernels, reaching 10-100x speedup over common machine learning operations in PyTorch. Our system is also able to produce highly optimized CUDA kernels that are much faster than existing CUDA kernels commonly used in production. We believe that fundamentally, AI systems can and should be as resource-efficient as the human brain, and that the best path to achieve this efficiency is to use AI to make AI more efficient! We are excited to publish our paper, The AI CUDA Engineer: Agentic CUDA Kernel Discovery, Optimization and Composition. We also release a dataset of over 17,000 verified CUDA kernels produced by The AI CUDA Engineer. Paper: Kernel Archive Webpage: HuggingFace Dataset: The AI CUDA Engineer utilizes evolutionary LLM-driven code optimization to autonomously improve the runtime of machine learning operations. Our system is not only able to convert PyTorch code into CUDA kernels, but through the use of evolution, it can also optimize the runtime performance of CUDA kernels, fuse multiple operations, and even discover novel solutions for writing efficient CUDA operations by learning from past innovations! We believe The AI CUDA Engineer opens a new era of AI-driven acceleration of AI and automated inference time optimization. We (Robert Lange, Aaditya Prasad 🇺🇸, Suuun, Maxence Faldor, Yujin Tang, hardmaru) are excited to continue Sakana AI's mission of leveraging AI to improve AI.
1:21

Introducing The AI CUDA Engineer: An agentic AI system that automates the production of highly optimized CUDA kernels. The AI CUDA Engineer can produce highly optimized CUDA kernels, reaching 10-100x speedup over common machine learning operations in PyTorch. Our system is also able to produce highly optimized CUDA kernels that are much faster than existing CUDA kernels commonly used in production. We believe that fundamentally, AI systems can and should be as resource-efficient as the human brain, and that the best path to achieve this efficiency is to use AI to make AI more efficient! We are excited to publish our paper, The AI CUDA Engineer: Agentic CUDA Kernel Discovery, Optimization and Composition. We also release a dataset of over 17,000 verified CUDA kernels produced by The AI CUDA Engineer. Paper: Kernel Archive Webpage: HuggingFace Dataset: The AI CUDA Engineer utilizes evolutionary LLM-driven code optimization to autonomously improve the runtime of machine learning operations. Our system is not only able to convert PyTorch code into CUDA kernels, but through the use of evolution, it can also optimize the runtime performance of CUDA kernels, fuse multiple operations, and even discover novel solutions for writing efficient CUDA operations by learning from past innovations! We believe The AI CUDA Engineer opens a new era of AI-driven acceleration of AI and automated inference time optimization. We (Robert Lange, Aaditya Prasad 🇺🇸, Suuun, Maxence Faldor, Yujin Tang, hardmaru) are excited to continue Sakana AI's mission of leveraging AI to improve AI.

Sakana AI

1,149,339 Aufrufe • vor 1 Jahr

Luminal fuses entire models into a single GPU kernel, automatically. Let's talk about why this matters for inference at the speed of light:
9:24

Luminal fuses entire models into a single GPU kernel, automatically. Let's talk about why this matters for inference at the speed of light:

Joe Fioti

24,348 Aufrufe • vor 5 Monaten

# FreeRTOS Kernel Teardown!! Working on porting the FreeRTOS kernel from scratch on a new target. Got the scheduler to kick off and switch between two tasks. It later runs into a crash... I am debugging that at the moment. I am going to dive into the details of the FreeRTOS Kernel implementation. The scheduler is a fancy version of what we hand coded as part of the "Cortex-M CPU - Programming a Round Robin Scheduler". It is available as youtube playlist - The FreeRTOS teardown and exploration will be included in the Firmware Engineering Bundle of courses: Use REBOOT50 at the checkout to get a 50% off.
0:20

# FreeRTOS Kernel Teardown!! Working on porting the FreeRTOS kernel from scratch on a new target. Got the scheduler to kick off and switch between two tasks. It later runs into a crash... I am debugging that at the moment. I am going to dive into the details of the FreeRTOS Kernel implementation. The scheduler is a fancy version of what we hand coded as part of the "Cortex-M CPU - Programming a Round Robin Scheduler". It is available as youtube playlist - The FreeRTOS teardown and exploration will be included in the Firmware Engineering Bundle of courses: Use REBOOT50 at the checkout to get a 50% off.

Piyush Itankar

14,420 Aufrufe • vor 1 Jahr

Ex-Google engineer reveals how to build AI agent loops, harnesses, LLM ops, and evals in 19 minutes. Trace → evaluate → diagnose → fix → ship → repeat. That loop is how agents self-improve over time. Agentic loops + harness + memory + evals - that’s the senior engineer stack. This is better than $500 paid courses on the same topic, explained in under 20 minutes. Watch it, then save the framework below.
20:10

Ex-Google engineer reveals how to build AI agent loops, harnesses, LLM ops, and evals in 19 minutes. Trace → evaluate → diagnose → fix → ship → repeat. That loop is how agents self-improve over time. Agentic loops + harness + memory + evals - that’s the senior engineer stack. This is better than $500 paid courses on the same topic, explained in under 20 minutes. Watch it, then save the framework below.

Codez

160,510 Aufrufe • vor 5 Tagen

Two days ago, Deepseek surprised everyone with an "undefined-behavior" PTX optimization speeding up particular ML workloads on a Hopper NVIDIA GPU Kernel. Let's reverse engineer the hack, implement it ourselves, and benchmark the speedup on an H100.
0:58

Two days ago, Deepseek surprised everyone with an "undefined-behavior" PTX optimization speeding up particular ML workloads on a Hopper NVIDIA GPU Kernel. Let's reverse engineer the hack, implement it ourselves, and benchmark the speedup on an H100.

LaurieWired

228,591 Aufrufe • vor 1 Jahr

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.
19:30

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.

Movez

548,034 Aufrufe • vor 7 Tagen

Writing a CUDA kernel requires a shift in mental model. Instead of one fast processor, you manage thousands of tiny threads. Here is the code and the logic explained for Matrix Multiplication.
4:10

Writing a CUDA kernel requires a shift in mental model. Instead of one fast processor, you manage thousands of tiny threads. Here is the code and the logic explained for Matrix Multiplication.

Ashutosh Maheshwari

189,009 Aufrufe • vor 7 Monaten

Missed today’s live Q&A on PyTorch 2.6? The full recording is now available on our LinkedIn & YouTube. PyTorch Core Maintainer Nikita Shulga (Meta) answered key questions about the latest release, sharing his insights on CUDA, torch.compile, security improvements and more. 📺 Watch the full session here: In this clip, Nikita breaks down a crucial topic: 👉 What are the challenges of benchmarking to avoid performance regressions in PyTorch releases? #pytorch #machinelearning #opensource #ai
1:08

Missed today’s live Q&A on PyTorch 2.6? The full recording is now available on our LinkedIn & YouTube. PyTorch Core Maintainer Nikita Shulga (Meta) answered key questions about the latest release, sharing his insights on CUDA, torch.compile, security improvements and more. 📺 Watch the full session here: In this clip, Nikita breaks down a crucial topic: 👉 What are the challenges of benchmarking to avoid performance regressions in PyTorch releases? #pytorch #machinelearning #opensource #ai

PyTorch

11,052 Aufrufe • vor 1 Jahr

Developer Advocate Suraj Subramanian talks all about PyTorch with Pascal Hartig on the latest Meta Tech Podcast. Learn about the history of #PyTorch, how it became successful, and the importance of fostering a helpful community. Listen now:
0:53

Developer Advocate Suraj Subramanian talks all about PyTorch with Pascal Hartig on the latest Meta Tech Podcast. Learn about the history of #PyTorch, how it became successful, and the importance of fostering a helpful community. Listen now:

Meta Open Source

25,544 Aufrufe • vor 3 Jahren

Linux Kernel is Now Vibe Coded Usage of AI (Claude, Codex, etc.) is exploding in the Linux world. At the current rate, the Linux Kernel will be predominantly developed using AI sometime this year.
13:53

Linux Kernel is Now Vibe Coded Usage of AI (Claude, Codex, etc.) is exploding in the Linux world. At the current rate, the Linux Kernel will be predominantly developed using AI sometime this year.

The Lunduke Journal

16,340 Aufrufe • vor 1 Monat

PyTorch Grows as the Dominant Open Source Framework for AI / ML 🔥 Read our #PyTorch 2024 Year in Review blog:
0:42

PyTorch Grows as the Dominant Open Source Framework for AI / ML 🔥 Read our #PyTorch 2024 Year in Review blog:

PyTorch

19,201 Aufrufe • vor 1 Jahr

FlexAttention is a novel compiler-driven programming model that allows implementing the majority of attention variants in a few lines of idiomatic PyTorch code Boyuan Feng & Avik Chaudhuri show how many existing attention variants can be implemented via FlexAttention & that we achieve competitive performance compared to handwritten kernels. 📺 Watch the full video on YouTube:
0:57

FlexAttention is a novel compiler-driven programming model that allows implementing the majority of attention variants in a few lines of idiomatic PyTorch code Boyuan Feng & Avik Chaudhuri show how many existing attention variants can be implemented via FlexAttention & that we achieve competitive performance compared to handwritten kernels. 📺 Watch the full video on YouTube:

PyTorch

17,929 Aufrufe • vor 1 Jahr

What if we turned Cardano into a single, shared liquidity layer? You might’ve seen the “DeFi Kernel” idea popping up on your timeline... Here’s what it’s all about.. and how Dano Finance fits into the vision
6:21

What if we turned Cardano into a single, shared liquidity layer? You might’ve seen the “DeFi Kernel” idea popping up on your timeline... Here’s what it’s all about.. and how Dano Finance fits into the vision

Linda

10,663 Aufrufe • vor 2 Monaten

Linus Torvalds, who created the Linux kernel, explains how what started as a simple experiment grew into one of the most powerful operating system…
1:18

Linus Torvalds, who created the Linux kernel, explains how what started as a simple experiment grew into one of the most powerful operating system…

Security Trybe

47,053 Aufrufe • vor 4 Monaten

timelapse #89 (12.5 hrs): - got single gpu nvfp4 gemm @ 5.2 PFLOPS working reliably (sm100) - solved ampere/hopper gemm kernel from scratch issues - split kernel optimization chapter into: - gemv, softmax, layernorm, topK, gemm (fp32 only cuda cores) - gemm (tf32, fp16, bf16, fp8, fp4) - cutting sugar made me feel great in the morning but killed me later in the day so went to bed super early - more hyperengineering tomorrow (ordered 96 diet cokes)
0:23

timelapse #89 (12.5 hrs): - got single gpu nvfp4 gemm @ 5.2 PFLOPS working reliably (sm100) - solved ampere/hopper gemm kernel from scratch issues - split kernel optimization chapter into: - gemv, softmax, layernorm, topK, gemm (fp32 only cuda cores) - gemm (tf32, fp16, bf16, fp8, fp4) - cutting sugar made me feel great in the morning but killed me later in the day so went to bed super early - more hyperengineering tomorrow (ordered 96 diet cokes)

Elliot Arledge

60,596 Aufrufe • vor 9 Monaten

The Nesa Playground abstracts the complexity of building away ⬟ Builders come in, create a DAI, plug into the stack, and tap into the community for launch. Get started on your Decentralized AI project today That loop is the product. DAIs built through use, not promises.
0:21

The Nesa Playground abstracts the complexity of building away ⬟ Builders come in, create a DAI, plug into the stack, and tap into the community for launch. Get started on your Decentralized AI project today That loop is the product. DAIs built through use, not promises.

Nesa

25,383 Aufrufe • vor 5 Monaten

You can build your 3D models directly from a prompt into Claude code. All thanks to this beautiful python project, build123 a parametric modeling framework for 2D and 3D CAD. It is built on the Open Cascade geometric kernel and it is suitable for 3D printing.
0:36

You can build your 3D models directly from a prompt into Claude code. All thanks to this beautiful python project, build123 a parametric modeling framework for 2D and 3D CAD. It is built on the Open Cascade geometric kernel and it is suitable for 3D printing.

Marco Franzon

20,777 Aufrufe • vor 3 Monaten

This is my favorite clip of the new Elon pod. He opens up saying xAI struggles with memory usage/bandwidth and CUDA kernel optimization (matmul, attention, MoE, etc). If you are good kernel or performance engineering in general, you should apply. Steer the world in a better direction.
0:37

This is my favorite clip of the new Elon pod. He opens up saying xAI struggles with memory usage/bandwidth and CUDA kernel optimization (matmul, attention, MoE, etc). If you are good kernel or performance engineering in general, you should apply. Steer the world in a better direction.

Elliot Arledge

163,922 Aufrufe • vor 5 Monaten

Good afternoon. Bitcoin breaks the channel. Bitcoin breaks the weekly kernel. Bitcoin rejects the 200 SMA Bitcoin rejects the 4 day Kernel. Bitcoin is extremely bearish.
3:07

Good afternoon. Bitcoin breaks the channel. Bitcoin breaks the weekly kernel. Bitcoin rejects the 200 SMA Bitcoin rejects the 4 day Kernel. Bitcoin is extremely bearish.

Philakone

20,529 Aufrufe • vor 1 Monat

Bring your friends, transform into a Magical Girl, and kill god in the multiplayer co-op roguelike action RPG Kernel Hearts. Join the multiplayer closed alpha now. #IGNSummerOfGaming
1:27

Bring your friends, transform into a Magical Girl, and kill god in the multiplayer co-op roguelike action RPG Kernel Hearts. Join the multiplayer closed alpha now. #IGNSummerOfGaming

IGN

49,338 Aufrufe • vor 1 Jahr