TUNE IN ON JUNE 10TH FOR a big announcement! RSVP to watch it live.

Democratizing AI Compute

Go behind the scenes of the AI industry in this blog series by Chris Lattner. Trace the evolution of AI compute, dissect its current challenges, and discover how Modular is raising the bar with the world’s most open inference stack.

Start reading now

View all posts

From the readers:

Really excellent reading material, for now and for later!

@tilli_fe

Love this series! Thanks for sharing

@RajaPatnaik

This is a great series, thank you@clattner_llvm!

@bradthilton

This is a very interesting read Chris Lattner. Thank you for sharing there. There’s always something new to learn from them. Please do keep them coming ☺️🙏🏾

Lezwon Castelino

Chris Lattner, keep them coming! They are breaths of fresh air

Alexey Myakov

Great insights into the evolution of CUDA and NVIDIA’s role in AI! It’s fascinating to see how early investments and strategy set the stage for today’s dominance.

Jan Dale Carlo Catalonia

This is an excellent series of write-ups, covering history, technology overview and market forces all in a 5-min read. Thank you Chris Lattner. Looking forward to part 4.

Mukesh Hira

The industry gets its wake-up call

DeepSeek's Impact on AI (Democratizing AI Compute, Part 1)

Part 1 of an article that explores the future of hardware acceleration for AI beyond CUDA, framed in the context of the release of DeepSeek

January 30, 2025

How CUDA paved the way

What exactly is “CUDA”? (Democratizing AI Compute, Part 2)

February 5, 2025

How did CUDA succeed? (Democratizing AI Compute, Part 3)

If we as an ecosystem hope to make progress, we need to understand how the CUDA software empire became so dominant.

February 12, 2025

CUDA is the incumbent, but is it any good? (Democratizing AI Compute, Part 4)

Answering the question of whether CUDA is “good” is much trickier than it sounds.

February 20, 2025

Lessons learned from CUDA alternatives

What about OpenCL and CUDA C++ alternatives? (Democratizing AI Compute, Part 5)

March 5, 2025

What about TVM, XLA, and AI compilers? (Democratizing AI Compute, Part 6)

March 12, 2025

What about Triton and Python eDSLs? (Democratizing AI Compute, Part 7)

In this post, we’ll break down how Python eDSLs work, their strengths and weaknesses, and take a close look at Triton.

March 26, 2025

What about the MLIR compiler infrastructure? (Democratizing AI Compute, Part 8)

April 8, 2025

Why do HW companies struggle to build AI software? (Democratizing AI Compute, Part 9)

April 22, 2025

Modular's approach

Modular’s bet to break out of the Matrix (Democratizing AI Compute, Part 10)

May 8, 2025

Subscribe to RSS feed

Get notified when new blog posts are published. Stay up to date with every insight from this series and more from Modular.

Copy RSS Feed URL

Follow Chris Lattner

Hear directly from Modular’s CEO on AI, systems, and the future of compute.

X (Twitter)

Follow Modular

Track Modular’s latest releases, research, and breakthroughs in AI infrastructure and tooling.