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.

this tool resolved a critical memory leak in minutes over the weekend, I built a lightweight performance monitor that tracks memory usage & trends across page sections – helping to pinpoint difficult problem area leaks & resolve them with an automatic prompt copy & paste the prompt + performance... show more

ty

6,752 subscribers

12,107 views • 5 months 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

Get Gemini up to speed on what matters most to you with memory import. Bring an understanding of your key preferences, relationships, and personal context directly into Gemini. Once you import these memories, Gemini will understand the same key facts you’ve shared with other AI apps, like your dietary restrictions, your sibling’s names, or where you grew up and securely save those details for your next chat. To get started: 1) Head to your Settings in Gemini and select “Import memory to Gemini.” 2) Ask your current AI: Copy our suggested prompt and paste it into your other AI app to generate a summary of your preferences and style. 3) Copy the response: Copy the personalized summary it creates for you. 4) Paste into Gemini: Go back to “Import memory to Gemini,” paste the text, and start a new chat.

Get Gemini up to speed on what matters most to you with memory import. Bring an understanding of your key preferences, relationships, and personal context directly into Gemini. Once you import these memories, Gemini will understand the same key facts you’ve shared with other AI apps, like your dietary restrictions, your sibling’s names, or where you grew up and securely save those details for your next chat. To get started: 1) Head to your Settings in Gemini and select “Import memory to Gemini.” 2) Ask your current AI: Copy our suggested prompt and paste it into your other AI app to generate a summary of your preferences and style. 3) Copy the response: Copy the personalized summary it creates for you. 4) Paste into Gemini: Go back to “Import memory to Gemini,” paste the text, and start a new chat.

Google Gemini

48,721 views • 3 months ago

“This is my memory, so maybe the fans [will say], ‘I don’t do that!’— but in my memory, I remember when [we] performed ‘Story Of My Life’ for the first time. [We] chose Japan as a place to perform this performance because [of the] sincere respect from the Japanese audience. If [we’d done] the performance [for example] in England, I'm sure they would scream or say something to the stage, but we did ‘Story Of My Life’ live in Japan. [We] performed a cappella. I think that was a performance that could not be realised outside of Japan. It was a magical moment. [It was] the first time we performed in such a way. That performance a cappella was the best moment. It's a memory of a lifetime.” -Louis on a special memory from Japan, via Front Row.

“This is my memory, so maybe the fans [will say], ‘I don’t do that!’— but in my memory, I remember when [we] performed ‘Story Of My Life’ for the first time. [We] chose Japan as a place to perform this performance because [of the] sincere respect from the Japanese audience. If [we’d done] the performance [for example] in England, I'm sure they would scream or say something to the stage, but we did ‘Story Of My Life’ live in Japan. [We] performed a cappella. I think that was a performance that could not be realised outside of Japan. It was a magical moment. [It was] the first time we performed in such a way. That performance a cappella was the best moment. It's a memory of a lifetime.” -Louis on a special memory from Japan, via Front Row.

HL Daily Media

520,542 views • 3 years ago

the best ads from notch customers. with the prompts that made them. copy a prompt. paste it into notch. ship your brand's version tonight. the prompts are in the comments. here's how each ad was made. → drop the input. a brief. an idea. a winning ad to recreate. → notch ad agent loads brand memory. strategizes the angle. produces the ad. → on-brand version renders. live to meta in one click. study them. copy them. modify for your brand. ship yours.

Vinay Jain

409,463 views • 27 days ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

159,484 views • 4 months ago

Problem: AI coding performance dips when context windows exceed 50% Solution: Combine Cline's context window awareness with the `new_task` tool + .clinerules to create a workflow that autonomously hands off tasks before hitting limits, ensuring persistent memory. A guide: 🧵

Problem: AI coding performance dips when context windows exceed 50% Solution: Combine Cline's context window awareness with the `new_task` tool + .clinerules to create a workflow that autonomously hands off tasks before hitting limits, ensuring persistent memory. A guide: 🧵

Cline

62,196 views • 1 year ago

Built a lightweight mobile SDK that lets our QA agent know exactly what's happening under the hood. It tracks: - CPU/memory performance - Network requests & failures - Screen transitions - Tap gestures - Full distributed traces Give an agent this level of context and it stops guessing why a new feature isn't working. It just reads the trace and fixes the code.

Built a lightweight mobile SDK that lets our QA agent know exactly what's happening under the hood. It tracks: - CPU/memory performance - Network requests & failures - Screen transitions - Tap gestures - Full distributed traces Give an agent this level of context and it stops guessing why a new feature isn't working. It just reads the trace and fixes the code.

Landseer Enga

31,001 views • 4 months ago

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

131,779 views • 1 year ago

We analyzed Anthropic’s memory architecture and built something better: a persistent, human-inspectable, and token-efficient memory layer that scales with your projects. Today, it’s OPEN-SOURCE. ByteRover CLI gives agents (like OpenClaw, Claude Code, and Hermes) persistent, structured memory. Built on the exact architecture that became the #1 memory system for OpenClaw (30,000+ downloads in a week), it lets developers curate project knowledge into a file-based hierarchy. This guarantees highly accurate, lightning-fast retrieval, even with lightweight models. 👉Highly Accurate: >92% retrieval accuracy across long-running sessions - the highest proven production accuracy on the market. ⚡Fast: ~1.6s average retrieval time. 💰Economic: Maintains >90% accuracy even with lightweight models, saving 50-70% on token costs. ☁ Portable: Runs locally by default, with cloud-sync to share memory across agents and teammates.

We analyzed Anthropic’s memory architecture and built something better: a persistent, human-inspectable, and token-efficient memory layer that scales with your projects. Today, it’s OPEN-SOURCE. ByteRover CLI gives agents (like OpenClaw, Claude Code, and Hermes) persistent, structured memory. Built on the exact architecture that became the #1 memory system for OpenClaw (30,000+ downloads in a week), it lets developers curate project knowledge into a file-based hierarchy. This guarantees highly accurate, lightning-fast retrieval, even with lightweight models. 👉Highly Accurate: >92% retrieval accuracy across long-running sessions - the highest proven production accuracy on the market. ⚡Fast: ~1.6s average retrieval time. 💰Economic: Maintains >90% accuracy even with lightweight models, saving 50-70% on token costs. ☁ Portable: Runs locally by default, with cloud-sync to share memory across agents and teammates.

andy nguyen

28,980 views • 3 months ago

16K texture painting on a 2015 1st Gen 9.7-inch iPad Pro, the least powerful iPad with Apple Pencil support. Wafer’s tool performance is barely affected by texture resolution or layer count. It is also optimized to run efficiently on low-memory devices.

16K texture painting on a 2015 1st Gen 9.7-inch iPad Pro, the least powerful iPad with Apple Pencil support. Wafer’s tool performance is barely affected by texture resolution or layer count. It is also optimized to run efficiently on low-memory devices.

Sparseal

33,267 views • 4 months ago

Investors: imagine cutting board meeting prep from hours to minutes with one prompt. Leveraging our MCP server, you can now unify information across Standard Metrics (Standard Metrics), Notion, Google Calendar, and other tools with a simple prompt, reducing board meeting prep and other admin to minutes. Watch the demo below to see how Claude (Anthropic): 1) Knows to search Google Calendar based on the prompt, pulling a list of company names 2) Finds those companies in Standard Metrics, aggregating performance data 3) Writes a quick performance summary with that context, updating Notion when asked This simple workflow delivers board-ready insights into how each is portfolio company is doing, minus the grunt work. Check out the video below 👇

Investors: imagine cutting board meeting prep from hours to minutes with one prompt. Leveraging our MCP server, you can now unify information across Standard Metrics (Standard Metrics), Notion, Google Calendar, and other tools with a simple prompt, reducing board meeting prep and other admin to minutes. Watch the demo below to see how Claude (Anthropic): 1) Knows to search Google Calendar based on the prompt, pulling a list of company names 2) Finds those companies in Standard Metrics, aggregating performance data 3) Writes a quick performance summary with that context, updating Notion when asked This simple workflow delivers board-ready insights into how each is portfolio company is doing, minus the grunt work. Check out the video below 👇

John Melas-Kyriazi

837,133 views • 11 months ago

How to create Farcaster mini app without coding - Step 1: > Go to ChatGPT > Just type: "I would like to create a Farcaster mini app, can you give me some ideas?" > Choose any one of the ideas - Note: - You can also type your own idea to ChatGPT and alter it - Step 2: - Go to ChatGPT > Paste the first prompt (shared in my channel) > Include the project you chose and tell ChatGPT to alter the prompt according to the idea below - Step 3 - Go to: > Sign up using Gmail or GitHub > Projects -> New Project -> Type the name of your project >Just paste the prompt we created earlier > It will start creating your app > If you need to alter anything, just go to GPT and type: [ I need a prompt to alter "your issue (like changing colour, etc.)" in my app already created in v0app by Vercel ] > Copy the prompt and paste it in v0 > No need to worry about errors , it will rectify them for you > If your project is finished, just click "Publish" on your top right > It will automatically host your app in Vercel > Click "Visit site" to see your app on another device and copy the website URL - Step 4 - Go to: v0 app > Just paste Prompt 2 from the file I provided > Click Publish once it’s completed - Step 5 - Go to: v0 app > Just paste the prompt 3 from the file I provided - Step 6 (Important) > Just paste Prompt 4 from the file I provided - Step 7 > Just paste Prompt 4 from the file I provided - Step 8 > Just paste Prompt 6 from the file I provided > It’s an important step to do — you need to create a manifest inside your app so that you can host it on Farcaster - Step 9 - Go to: > Sign up or Login > Settings → Developers → Mini Apps → Create Manifest (New) > Paste your website URL (remove https) > It should be like: > If you find any error while doing this, just copy and paste it in the v0 app > Once everything is finished, you need to create Account Association > Scan the QR on your mobile and tap and hold the Yes button > It will show an error — just copy and paste those errors into the v0 app > Click Publish again, and then click Refresh in Manifest > Click Open your app > for the main prompt file check our tg channel link in our bio

How to create Farcaster mini app without coding - Step 1: > Go to ChatGPT > Just type: "I would like to create a Farcaster mini app, can you give me some ideas?" > Choose any one of the ideas - Note: - You can also type your own idea to ChatGPT and alter it - Step 2: - Go to ChatGPT > Paste the first prompt (shared in my channel) > Include the project you chose and tell ChatGPT to alter the prompt according to the idea below - Step 3 - Go to: > Sign up using Gmail or GitHub > Projects -> New Project -> Type the name of your project >Just paste the prompt we created earlier > It will start creating your app > If you need to alter anything, just go to GPT and type: [ I need a prompt to alter "your issue (like changing colour, etc.)" in my app already created in v0app by Vercel ] > Copy the prompt and paste it in v0 > No need to worry about errors , it will rectify them for you > If your project is finished, just click "Publish" on your top right > It will automatically host your app in Vercel > Click "Visit site" to see your app on another device and copy the website URL - Step 4 - Go to: v0 app > Just paste Prompt 2 from the file I provided > Click Publish once it’s completed - Step 5 - Go to: v0 app > Just paste the prompt 3 from the file I provided - Step 6 (Important) > Just paste Prompt 4 from the file I provided - Step 7 > Just paste Prompt 4 from the file I provided - Step 8 > Just paste Prompt 6 from the file I provided > It’s an important step to do — you need to create a manifest inside your app so that you can host it on Farcaster - Step 9 - Go to: > Sign up or Login > Settings → Developers → Mini Apps → Create Manifest (New) > Paste your website URL (remove https) > It should be like: > If you find any error while doing this, just copy and paste it in the v0 app > Once everything is finished, you need to create Account Association > Scan the QR on your mobile and tap and hold the Yes button > It will show an error — just copy and paste those errors into the v0 app > Click Publish again, and then click Refresh in Manifest > Click Open your app > for the main prompt file check our tg channel link in our bio

Maran

48,106 views • 7 months ago

So happy to share this excerpt from Pli selon pli, with Pierre Boulez conducting, from our performance in Amsterdam on tour in 2011 with Ensemble intercontemporain and musicians from the Luzern Festival. A very special and cherished memory

So happy to share this excerpt from Pli selon pli, with Pierre Boulez conducting, from our performance in Amsterdam on tour in 2011 with Ensemble intercontemporain and musicians from the Luzern Festival. A very special and cherished memory

Barbara Hannigan

12,767 views • 1 year ago

How to get the ‘Taste Your Own Medicine’ trophy in Assassin’s Creed Mirage Valley of Memory DLC. Use the Blowdart tool with the Tier 2 Lethal Dose perk activated. Find an enemy carrying a green sword, then use the tool on them.

How to get the ‘Taste Your Own Medicine’ trophy in Assassin’s Creed Mirage Valley of Memory DLC. Use the Blowdart tool with the Tier 2 Lethal Dose perk activated. Find an enemy carrying a green sword, then use the tool on them.

Zephryss⛩️

32,600 views • 7 months ago

Flaky tests and memory leaks are the worst. Vitest now has a --detect-async-leaks flag that catches uncleared intervals, lingering servers, and other async operations leaking across your tests. ⚠️ Don't run it on every run though. Use it to audit your test suite, then clean things up. Available in the latest 4.1 beta. Big shout out to Ari from the Vitest team for landing this PR! 🔥

Flaky tests and memory leaks are the worst. Vitest now has a --detect-async-leaks flag that catches uncleared intervals, lingering servers, and other async operations leaking across your tests. ⚠️ Don't run it on every run though. Use it to audit your test suite, then clean things up. Available in the latest 4.1 beta. Big shout out to Ari from the Vitest team for landing this PR! 🔥

VoidZero

49,255 views • 5 months ago

Excited to share a first look at the Orion Dashboard! It’s designed to help our community easily monitor Orion validator nodes, track performance metrics like CPU, memory, and more—all while aligning with our focus on renewable energy. This is just the beginning as we work toward a greener, decentralized future. $DIONE

Excited to share a first look at the Orion Dashboard! It’s designed to help our community easily monitor Orion validator nodes, track performance metrics like CPU, memory, and more—all while aligning with our focus on renewable energy. This is just the beginning as we work toward a greener, decentralized future. $DIONE

Stefan

60,462 views • 1 year ago

🚨 launch alert 🚨 most SEO audit tools give you a tacky report and leave you stuck with jargon and numbers in red - they never tell you how to fix it so I built something different 👉 enter your domain and get a clean SEO report with a ready-to-use PROMPT you copy & paste straight into ChatGPT, Claude, or Cursor to fix everything get a full crawl across 8 SEO pillars - foundation, content, metadata, performance, crawl & index, media, architecture, and AI search readiness every issue is flagged, prioritized, and explained 100% free - no setup, just takes a few seconds go fix your SEO 💥 (600+ websites audited in the last 24 hours btw 👀)

🚨 launch alert 🚨 most SEO audit tools give you a tacky report and leave you stuck with jargon and numbers in red - they never tell you how to fix it so I built something different 👉 enter your domain and get a clean SEO report with a ready-to-use PROMPT you copy & paste straight into ChatGPT, Claude, or Cursor to fix everything get a full crawl across 8 SEO pillars - foundation, content, metadata, performance, crawl & index, media, architecture, and AI search readiness every issue is flagged, prioritized, and explained 100% free - no setup, just takes a few seconds go fix your SEO 💥 (600+ websites audited in the last 24 hours btw 👀)

Tibo

22,378 views • 3 months ago

I just built this CRACKED Cursor MCP extension that makes your IDE fully aware of all the logs in your browser. Was struggling with a few issues recently and kept having to copy/paste logs but with this tool you can: ✅ Check all console logs + errors ✅ Analyze network requests, responses and errors ✅ Make changes to a selected element in your browser ✅ Take screenshots of your browser ... without EVER having to leave your IDE 🦾 Open source, FREE and compatible with Cursor, Cline, Continue and Zed. Link to the docs with setup instructions down below 👇

I just built this CRACKED Cursor MCP extension that makes your IDE fully aware of all the logs in your browser. Was struggling with a few issues recently and kept having to copy/paste logs but with this tool you can: ✅ Check all console logs + errors ✅ Analyze network requests, responses and errors ✅ Make changes to a selected element in your browser ✅ Take screenshots of your browser ... without EVER having to leave your IDE 🦾 Open source, FREE and compatible with Cursor, Cline, Continue and Zed. Link to the docs with setup instructions down below 👇

Ted Werbel

179,882 views • 1 year ago

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,406 views • 1 year ago

The latest MLX has a CUDA back-end! To get started: pip install "mlx[cuda]" With the same codebase you can develop locally, run your model on Apple silicon, or in the cloud on Nvidia GPUs. MLX is designed around Apple silicon - which has a unified memory architecture. It uses the same design with CUDA. So there's no need to move arrays around from CPU memory to GPU memory. Note, this is early days - some operations are missing and performance is still being optimized. But it's already quite fast for Transformer training, text generation, and more! Here's a demo using mlx-lm to generate text with Llama 3 8B (bf16) on an A100:

The latest MLX has a CUDA back-end! To get started: pip install "mlx[cuda]" With the same codebase you can develop locally, run your model on Apple silicon, or in the cloud on Nvidia GPUs. MLX is designed around Apple silicon - which has a unified memory architecture. It uses the same design with CUDA. So there's no need to move arrays around from CPU memory to GPU memory. Note, this is early days - some operations are missing and performance is still being optimized. But it's already quite fast for Transformer training, text generation, and more! Here's a demo using mlx-lm to generate text with Llama 3 8B (bf16) on an A100:

Awni Hannun

42,761 views • 11 months ago