iiinova — where your digital self keeps evolving

Modular: Inference from Kernel to Cloud [Unofficial]

@modular.com.web.brid.gy

10 followers 0 following 236 posts

The unified AI inference stack - from custom GPU kernels to production cloud serving on NVIDIA and AMD. 2x performance. Top open models. Open source stack. 🌉 bridged from 🌐 modular.com: fed.brid.gy/web/modular.com

Posts Replies Media

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 17/09/2026

Modular: Modular 26.6: Open compiler contributions, audio generation, and expanded model support

Modular 26.6: Open compiler contributions, audio generation, and expanded model support

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 18/08/2026

Modular: Mojo🔥 is now open source!

Mojo🔥 is now open source!

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 18/08/2026

Modular: ModCon 2026: Open source, open cloud, open silicon

ModCon 2026: Open source, open cloud, open silicon

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 29/07/2026

Modular: Qualcomm Completes Acquisition of Modular

Qualcomm Completes Acquisition of Modular

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 24/06/2026

Modular: Qualcomm to Acquire Modular

Qualcomm to Acquire Modular

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 18/06/2026

Modular: Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and More

Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and More

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 17/06/2026

Modular: ModCon 2026: Modular’s Developer Conference

ModCon 2026: Modular’s Developer Conference

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 11/06/2026

Modular: Day Zero: MiniMax M3 Open Weights on Modular Cloud

Day Zero: MiniMax M3 Open Weights on Modular Cloud

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 10/06/2026

Modular: Modverse #55: Mojo 1.0 Beta, Community Mojo Libraries, and Real-Time Patient Conversations Powered by MAX

Modverse #55: Mojo 1.0 Beta, Community Mojo Libraries, and Real-Time Patient Conversations Powered by MAX

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 05/06/2026

Modular: Why LLM Inference Needs a New Kind of Router - Part 3

Why LLM Inference Needs a New Kind of Router - Part 3

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 29/05/2026

Modular: Three trends from MLSys 2026

Three trends from MLSys 2026

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 21/05/2026

Modular: Why LLM Inference Needs a New Kind of Router - Part 2

Why LLM Inference Needs a New Kind of Router - Part 2

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 19/05/2026

Modular: How I built a pure Mojo app (and 10 libraries) with AI agents

How I built a pure Mojo app (and 10 libraries) with AI agents

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 18/05/2026

Modular: Hippocratic AI partners with Modular to power flexible, high-quality inference for real-time patient conversations

Hippocratic AI partners with Modular to power flexible, high-quality inference for real-time patient conversations

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 13/05/2026

Modular: Translating to Mojo via AI Agents

Translating to Mojo via AI Agents

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 12/05/2026

Modular: Inkwell: Why Your Inference Platform Matters As Much As Your Model

Inkwell: Why Your Inference Platform Matters As Much As Your Model

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 08/05/2026

Modular: Why LLM Inference Needs a New Kind of Router - Part 1

Why LLM Inference Needs a New Kind of Router - Part 1

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 07/05/2026

Modular: Modular 26.3: Mojo 1.0 Beta, MAX Video Gen, and more

Modular 26.3: Mojo 1.0 Beta, MAX Video Gen, and more

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 04/05/2026

Modular: Modverse #54: AMD AI DevDay, New Modular Offices, and a Community That Keeps Shipping

Modverse #54: AMD AI DevDay, New Modular Offices, and a Community That Keeps Shipping

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 16/04/2026

Modular: How Frontier Coding Agents Built a Video Diffusion Pipeline on MAX

How Frontier Coding Agents Built a Video Diffusion Pipeline on MAX

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 13/04/2026

Modular: TileTensor Part 1 - Safer, More Efficient GPU Kernels

TileTensor Part 1 - Safer, More Efficient GPU Kernels

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 10/04/2026

Modular: Modular Opens Edinburgh & San Francisco Offices

Modular Opens Edinburgh & San Francisco Offices

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 02/04/2026

Modular: Day Zero Launch: Fastest Performance for Gemma 4 on NVIDIA and AMD

Day Zero Launch: Fastest Performance for Gemma 4 on NVIDIA and AMD

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 31/03/2026

Modular: Modverse #54: From GTC to Edinburgh, a Community Building Momentum

Modverse #54: From GTC to Edinburgh, a Community Building Momentum

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 30/03/2026

Modular: Software Pipelining for GPU Kernels: Part 1 - The Pipeline Problem

Software Pipelining for GPU Kernels: Part 1 - The Pipeline Problem

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 26/03/2026

Modular: Structured Mojo Kernels Part 3 - Composition in Practice

Structured Mojo Kernels Part 3 - Composition in Practice

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 19/03/2026

Modular: Modular 26.2: State-of-the-Art Image Generation and Upgraded AI Coding with Mojo

Modular 26.2: State-of-the-Art Image Generation and Upgraded AI Coding with Mojo

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 16/03/2026

Modular: Modular at NVIDIA GTC 2026: MAX on Blackwell, Mojo Kernel Porting, and DeepSeek V3 on B200

Modular at NVIDIA GTC 2026: MAX on Blackwell, Mojo Kernel Porting, and DeepSeek V3 on B200

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 11/03/2026

Modular: Structured Mojo Kernels Part 2 - The Three Pillars

Structured Mojo Kernels Part 2 - The Three Pillars

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 06/03/2026

Modular: Modverse #53: Community Builds, Research Milestones, and a Growing Ecosystem

Modverse #53: Community Builds, Research Milestones, and a Growing Ecosystem

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 04/03/2026

Modular: Structured Mojo Kernels Part 1 - Peak Performance, Half the Code

Structured Mojo Kernels Part 1 - Peak Performance, Half the Code

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 27/02/2026

Modular: Structured Mojo Kernels Part 1 - Why Structured Kernels?

Structured Mojo Kernels Part 1 - Why Structured Kernels?

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 18/02/2026

Modular: The Claude C Compiler: What It Reveals About the Future of Software

The Claude C Compiler: What It Reveals About the Future of Software

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 10/02/2026

Modular: BentoML Joins Modular

BentoML Joins Modular

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 05/02/2026

Modular: The Five Eras of KVCache

The Five Eras of KVCache

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 29/01/2026

Modular: Modular 26.1: A Big Step Towards More Programmable and Portable AI Infrastructure

Modular 26.1: A Big Step Towards More Programmable and Portable AI Infrastructure

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 14/01/2026

Modular: How to Beat Unsloth's CUDA Kernel Using Mojo—With Zero GPU Experience

How to Beat Unsloth's CUDA Kernel Using Mojo—With Zero GPU Experience

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 12/01/2026

Modular: How I Beat Unsloth's CUDA Kernel Using Mojo—With Zero GPU Experience

How I Beat Unsloth's CUDA Kernel Using Mojo—With Zero GPU Experience

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 19/12/2025

Modular: 🔥 Modular 2025 Year in Review

🔥 Modular 2025 Year in Review

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 05/12/2025

Modular: The path to Mojo 1.0

The path to Mojo 1.0

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 03/12/2025

Modular: Modverse #52: Advancing AI Together — Community Projects & Platform Milestones

Modverse #52: Advancing AI Together — Community Projects & Platform Milestones

000

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 20/11/2025

Modular: Modular 25.7: Faster Inference, Safer GPU Programming, and a More Unified Developer Experience

Modular 25.7: Faster Inference, Safer GPU Programming, and a More Unified Developer Experience

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 07/11/2025

Modular: "TTS 1 Max" (powered by Modular Platform) Ranked #1 Speech Model on Artificial Analysis

"TTS 1 Max" (powered by Modular Platform) Ranked #1 Speech Model on Artificial Analysis

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 06/11/2025

Modular: PyTorch and LLVM in 2025 — Keeping up With AI Innovation

PyTorch and LLVM in 2025 — Keeping up With AI Innovation

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 17/10/2025

Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days

Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 24/09/2025

Modular: Modular Raises $250M to scale AI's Unified Compute Layer

Modular Raises $250M to scale AI's Unified Compute Layer

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 22/09/2025

Modular: Modular 25.6: Unifying the latest GPUs from NVIDIA, AMD, and Apple

Modular 25.6: Unifying the latest GPUs from NVIDIA, AMD, and Apple

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 19/09/2025

Modular: Matrix Multiplication on Blackwell: Part 4 - Breaking SOTA

Matrix Multiplication on Blackwell: Part 4 - Breaking SOTA

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 12/09/2025

Modular: Matrix Multiplication on Blackwell: Part 3 - The Optimizations Behind 85% of SOTA Performance

Matrix Multiplication on Blackwell: Part 3 - The Optimizations Behind 85% of SOTA Performance

Modular: Inference from Kernel to Cloud [Unofficial] @modular.com.web.brid.gy · 05/09/2025

Modular: Matrix Multiplication on Blackwell: Part 2 - Using Hardware Features to Optimize Matmul

Matrix Multiplication on Blackwell: Part 2 - Using Hardware Features to Optimize Matmul