The Curious Engineer

All blogs / AI / ML

Modular Blog

modular.com/blog

Thoughtful perspectives on high-performance AI, modern infrastructure, and the tools shaping the next generation of computing.

AI / MLOther languagesPerformance / optimization

’24’25’26
Posts
162 from 9 Jul 2024 to 22 Oct 2026
Posting
weekly (109 in the last year)
Kind
company blog
Feed
https://www.modular.com/blog/rss.xml

2026 103

  1. Modular: MAX is now source available and open to everyone
  2. Modular: Modular 26.7: Opening up MAX
  3. Modular: Announcing MAX Developer Edition Preview
  4. Modular: Modular to bring NVIDIA Accelerated Computing to the MAX Platform
  5. Modular: Nurturing the Modular ecosystem: the Modular Community Grant Program
  6. Modular: Modular 26.6: Open compiler contributions, audio generation, and expanded model support
  7. Modular: Mojo🔥 is now open source!
  8. Modular: Modular and Qualcomm: Same code, new silicon
  9. Modular: ModCon 2026: Open source, open cloud, open silicon
  10. Modular: Modular 26.5: Mojo 1.0 is here!
  11. Modular: Qualcomm Completes Acquisition of Modular
  12. Modular: Qualcomm to Acquire Modular
  13. Modular: Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and More
  14. Modular: ModCon 2026: Modular’s Developer Conference
  15. Modular: Day Zero: MiniMax M3 Open Weights on Modular Cloud
  16. Modular: Modverse #55: Mojo 1.0 Beta, Community Mojo Libraries, and Real-Time Patient Conversations Powered by MAX
  17. Modular: Why LLM Inference Needs a New Kind of Router - Part 3
  18. Modular: Three trends from MLSys 2026
  19. Modular: Why LLM Inference Needs a New Kind of Router - Part 2
  20. Modular: How I built a pure Mojo app (and 10 libraries) with AI agents
  21. Modular: Hippocratic AI partners with Modular to power flexible, high-quality inference for real-time patient conversations
  22. Modular: Translating to Mojo via AI Agents
  23. Modular: Inkwell: Why Your Inference Platform Matters As Much As Your Model
  24. Modular: Why LLM Inference Needs a New Kind of Router - Part 1
  25. Modular: Modular 26.3: Mojo 1.0 Beta, MAX Video Gen, and more
  26. Modular: Modverse #54: AMD AI DevDay, New Modular Offices, and a Community That Keeps Shipping
  27. Modular: How Frontier Coding Agents Built a Video Diffusion Pipeline on MAX
  28. Modular: TileTensor Part 1 - Safer, More Efficient GPU Kernels
  29. Modular: Modular Opens Edinburgh & San Francisco Offices
  30. Modular: Structured Mojo Kernels Part 4 - Portability and the Road Ahead
  31. Modular: Day Zero Launch: Fastest Performance for Gemma 4 on NVIDIA and AMD
  32. Modular: Modverse #54: From GTC to Edinburgh, a Community Building Momentum
  33. Modular: Software Pipelining for GPU Kernels: Part 1 - The Pipeline Problem
  34. Modular: Structured Mojo Kernels Part 3 - Composition in Practice
  35. Modular: Modular 26.2: State-of-the-Art Image Generation and Upgraded AI Coding with Mojo
  36. Modular: Modular at NVIDIA GTC 2026: MAX on Blackwell, Mojo Kernel Porting, and DeepSeek V3 on B200
  37. Modular: Structured Mojo Kernels Part 2 - The Three Pillars
  38. Modular: Modverse #53: Community Builds, Research Milestones, and a Growing Ecosystem
  39. Modular: Structured Mojo Kernels Part 1 - Peak Performance, Half the Code
  40. Modular: Mojo🔥 is now available on Mac
  41. Modular: The Claude C Compiler: What It Reveals About the Future of Software
  42. Modular: BentoML Joins Modular
  43. Modular: The Five Eras of KVCache
  44. Modular: Modular 26.1: A Big Step Towards More Programmable and Portable AI Infrastructure
  45. Modular: How to Beat Unsloth's CUDA Kernel Using Mojo—With Zero GPU Experience
  46. Modular: A brief guide to the Mojo n-body example
  47. Modular: A unified, extensible platform to superpower your AI
  48. Modular: Accelerating AI model serving with the Modular AI Engine
  49. Modular: AI Regulation: step with care, and great tact
  50. Modular: AI’s compute fragmentation: what matrix multiplication teaches us
  51. Modular: An easy introduction to Mojo🔥 for Python programmers
  52. Modular: Community Spotlight: How I built llama2.🔥 by Aydyn Tairov
  53. Modular: Deep dive into ownership in Mojo
  54. Modular: Develop locally, deploy globally
  55. Modular: Developer Voices: Deep Dive with Chris Lattner on Mojo
  56. Modular: Do LLMs eliminate the need for programming languages?
  57. Modular: Fast⚡k-means clustering in Mojo🔥: a guide to porting Python to Mojo🔥 for accelerated k-means clustering
  58. Modular: Getting started with MAX Developer Edition
  59. Modular: How to Be Confident in Your Performance Benchmarking
  60. Modular: How to setup a Mojo🔥 development environment with Docker containers
  61. Modular: If AI serving tech can’t solve today’s problems, how do we scale into the future?
  62. Modular: Increasing development velocity of giant AI models
  63. Modular: Part 2: Increasing development velocity of giant AI models
  64. Modular: Key announcements from ModCon 2023
  65. Modular: MAX 24.2 is Here! What’s New?
  66. Modular: MAX 24.3 - Introducing MAX Engine Extensibility
  67. Modular: MAX 24.4 - Introducing quantization APIs and MAX on macOS
  68. Modular: MAX is here! What does that mean for Mojo🔥?
  69. Modular: ModCon 2023 sessions you don’t want to miss!
  70. Modular: ModCon Mojo 🔥 Contest
  71. Modular: Modular is rebuilding AI in the face of a new economy
  72. Modular: Modular natively supports dynamic shapes for AI workloads
  73. Modular: Modular partners with Amazon Web Services (AWS) to bring MAX to AWS services
  74. Modular: Modular's Brand Story
  75. Modular: Mojo 🔥 Advent of Code 2023
  76. Modular: Mojo🔥 - It’s finally here!
  77. Modular: Mojo 🔥 lightning talk ⚡️ one language for all AI programming!
  78. Modular: Mojo 🔥 - A systems programming language presented at LLVM 2023
  79. Modular: Mojo🔥 ❤️ Pi 🥧: Approximating Pi with Mojo🔥 using Monte Carlo methods
  80. Modular: Mojo🔥 ♥️ Python: Calculating and plotting a Valentine’s day ♥️ using Mojo and Python
  81. Modular: Mojo🔥 SDK v0.7 now available for download!
  82. Modular: Mojo 🔥 Traits Have Arrived!
  83. Modular: Mojo vs. Rust: what are the differences?
  84. Modular: Our launch & what's next
  85. Modular: Row-major vs. Column-major Matrices: A Performance Analysis in Mojo and NumPy
  86. Modular: Semantic Search with MAX Engine
  87. Modular: Take control of your AI
  88. Modular: The Case for a Next-Generation AI Developer Platform
  89. Modular: The future of AI depends on Modularity
  90. Modular: The Next Big Step in Mojo🔥 Open Source
  91. Modular: The world's fastest unified matrix multiplication
  92. Modular: Using Mojo🔥 with Python🐍
  93. Modular: We want to hear from you
  94. Modular: Welcome Mostafa Hagog to Modular
  95. Modular: We’ve raised $100M to fix AI infrastructure for the world's developers
  96. Modular: What is loop unrolling? How you can speed up Mojo🔥 code with @unroll
  97. Modular: What ownership is really about: a mental model approach
  98. Modular: What's new in MAX 24.4? MAX on macOS, fast local Llama3, native quantization and GGUF support
  99. Modular: What’s new in Mojo 24.2: Mojo Nightly, Enhanced Python Interop, OSS stdlib and more
  100. Modular: What’s New in Mojo 24.3: Community Contributions, Pythonic Collections and Core Language Enhancements
  101. Modular: What’s new in Mojo 24.4? Improved collections, new traits, os module features and core language enhancements
  102. Modular: What’s new in Mojo SDK v0.5?
  103. Modular: What’s the difference between the AI Engine and Mojo?

2025 47

  1. Modular: 🔥 Modular 2025 Year in Review
  2. Modular: The path to Mojo 1.0
  3. Modular: Modverse #52: Advancing AI Together — Community Projects & Platform Milestones
  4. Modular: Modular 25.7: Faster Inference, Safer GPU Programming, and a More Unified Developer Experience
  5. Modular: "TTS 1 Max" (powered by Modular Platform) Ranked #1 Speech Model on Artificial Analysis
  6. Modular: PyTorch and LLVM in 2025 — Keeping up With AI Innovation
  7. Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
  8. Modular: Modular Raises $250M to scale AI's Unified Compute Layer
  9. Modular: Modular 25.6: Unifying the latest GPUs from NVIDIA, AMD, and Apple
  10. Modular: Matrix Multiplication on Blackwell: Part 4 - Breaking SOTA
  11. Modular: Modverse #51: Modular x Inworld x Oracle, Modular Meetup Recap and Community Projects
  12. Modular: Matrix Multiplication on Blackwell: Part 3 - The Optimizations Behind 85% of SOTA Performance
  13. Modular: Matrix Multiplication on Blackwell: Part 2 - Using Hardware Features to Optimize Matmul
  14. Modular: Matrix Multiplication on Blackwell: Part 1 - Introduction
  15. Modular: Modverse #50: Modular Platform 25.5, Community Meetups, and Mojo's Debut in the Stack Overflow Developer Survey
  16. Modular: Modular Platform 25.5: Introducing Large Scale Batch Inference
  17. Modular: SF Compute and Modular Partner to Revolutionize AI Inference Economics
  18. Modular: AI Agents for AWS Marketplace
  19. Modular: Modverse #49: Modular Platform 25.4, Modular 🤝 AMD, and Modular Hack Weekend
  20. Modular: Inside Modular Hack Weekend: Top Projects and Community Highlights
  21. Modular: How is Modular Democratizing AI Compute? (Democratizing AI Compute, Part 11)
  22. Modular: Modular 25.4: One Container, AMD and NVIDIA GPUs, No Lock-In
  23. Modular: Introducing Mammoth: Enterprise-Scale GenAI Deployments Made Simple
  24. Modular: Modular + AMD: Unleashing AI performance on AMD GPUs
  25. Modular: Modverse #48: Modular Platform 25.3, MAX AI Kernels, and the Modular GPU Kernel Hackathon
  26. Modular: Exploring Metaprogramming in Mojo
  27. Modular: Modular GPU Kernel Hackathon Highlights: Innovation, Community, & Mojo🔥
  28. Modular: Modular’s bet to break out of the Matrix (Democratizing AI Compute, Part 10)
  29. Modular: Modular Platform 25.3: 450K+ Lines of Open Source Code and pip Packaging
  30. Modular: A New, Simpler License for MAX and Mojo
  31. Modular: Why do HW companies struggle to build AI software? (Democratizing AI Compute, Part 9)
  32. Modular: Modverse #47: MAX 25.2 and an evening of GPU programming at Modular HQ
  33. Modular: What about the MLIR compiler infrastructure? (Democratizing AI Compute, Part 8)
  34. Modular: What about Triton and Python eDSLs? (Democratizing AI Compute, Part 7)
  35. Modular: MAX 25.2: Unleash the power of your H200's–without CUDA!
  36. Modular: What about TVM, XLA, and AI compilers? (Democratizing AI Compute, Part 6)
  37. Modular: What about OpenCL and CUDA C++ alternatives? (Democratizing AI Compute, Part 5)
  38. Modular: Modverse #46: MAX 25.1, MAX Builds, and Democratizing AI Compute
  39. Modular: CUDA is the incumbent, but is it any good? (Democratizing AI Compute, Part 4)
  40. Modular: MAX 25.1 - Introducing MAX Builds
  41. Modular: How did CUDA succeed? (Democratizing AI Compute, Part 3)
  42. Modular: Paged Attention & Prefix Caching Now Available in MAX Serve
  43. Modular: What exactly is “CUDA”? (Democratizing AI Compute, Part 2)
  44. Modular: Agentic Building Blocks: Creating AI Agents with MAX Serve and OpenAI Function Calling
  45. Modular: DeepSeek's Impact on AI (Democratizing AI Compute, Part 1)
  46. Modular: Use MAX with Open WebUI for RAG and Web Search
  47. Modular: Hands-on with Mojo 24.6

2024 11

  1. Modular: Evaluating Llama Guard with MAX 24.6 and Hugging Face
  2. Modular: Build a Continuous Chat Interface with Llama 3 and MAX Serve
  3. Modular: Introducing MAX 24.6: A GPU Native Generative AI Platform
  4. Modular: MAX GPU: State of the Art Throughput on a New GenAI platform
  5. Modular: Understanding SIMD: Infinite Complexity of Trivial Problems
  6. Modular: Community Spotlight: Writing Mojo with Cursor
  7. Modular: Hands-on with Mojo 24.5
  8. Modular: MAX 24.5 - With SOTA CPU Performance for Llama 3.1
  9. Modular: Announcing stack-pr: an open source tool for managing stacked PRs on GitHub
  10. Modular: Debugging in Mojo🔥
  11. Modular: Bring your own PyTorch model

Undated 1

  1. Evaluating max engine inference accuracy on the imagenet dataset