Chris Lattner
@clattner_llvm
Building beautiful things like Mojo🔥 and MAX @Modular, lifting the world of production AI/ML software into a new phase of innovation. We’re hiring! 🚀🧠
Last chance! Our GPU comic promo wraps up at the end of this week. Repost + tag @modular with #gpucomic to grab a limited-edition GPU Problems t-shirt (we'll DM you to coordinate shipping – make sure your DMs are open!).
🔥 Got GPU Problems? We feel you! 🔥 🤣 Might as well laugh while we change the world. 🚀 RT + tag @modular with #gpucomic to claim a GPU Problems t-shirt! Share your own GPU horror stories to be featured in future comic editions! 👇 comic.modular.com
Super excited to partner with @inworld_ai on their 20x cheaper, state-of-the-art text-to-speech model. Go try it now free! 🆓 Our technical achievements with @inworld_ai enabled the lowest latency, fastest TTS inference platform available on @NVIDIA B200 🚀 We'll be dropping a…
We just made state-of-the-art TTS 20x more affordable. $5 per million characters. And we're open sourcing the training and modeling code (built on Llama). Because scaling voice AI shouldn't break your budget. Technical Details → Inworld.ai/blog/introduci… Why and how we did it…
It was fun to nerd out with Richard of @sw_unscripted about programming languages in the modern era. At timestamp 46:01 I answer a FAQ: Why care about programming languages in the age of AI coding tools? Let me know what you think!
Episode 109: GPU Programming and Language Design with @clattner_llvm! 🎉
New in MAX nightly: provide an entire MAX graph as a PyTorch custom op with the `@graph_op` decorator! This makes it easier to use everything from individual MAX kernels to full subgraphs within your existing PyTorch models. Example in our GitHub repo: github.com/modular/modula…
Part 2 of my deep-dive into GPU programming with Mojo is live! I unpack sliding-window pooling, halo edges, prefix sums, & 2D indexing quirks, with sketches & code. Huge thanks to @Modular and @ehsanmok 🙌 Your puzzles & @Manim viz sparked this dive. Read: shubhamg.in/posts/2025-07-…
Did you know that our kernel library is open source and ready for community contributions? Build a high-performance kernel in Mojo for your favorite hardware, and make a meaningful impact across the AI ecosystem (and secure awesome swag 😎). Here's a list of kernels we’d love to…
Excited to announce the @Modular x @TensorWaveCloud partnership! "With this integration, teams can now serve the same workloads for 60–70% less cost—or handle 3–7x more traffic without increasing their budget" Huge win for ML teams looking to scale efficiently! Read the full…
TensorWave + @Modular deliver better inference performance at a fraction of the cost. If you’re serving billions of tokens, the math isn’t even close. See the breakdown → na2.hubs.ly/y0vMMG0
MAX isn’t just accelerator-agnostic, it’s accelerator-optimized. Running on @tensorwavecloud MI325X GPUs, MAX delivers up to 70% lower inference costs and faster throughput than H200 + vLLM. Same models. Better performance. 📊 See the results → tensorwave.com/blog/save-up-t…
It was wonderful getting to spend time with Henry and the AGIHouse team with a recent hackathon. I loved getting to nerd out with him about the future of human potential and unlocking creativity of Python developers in the new era of GPU compute!
Most AI devs are standing on legacy foundations. CUDA wasn’t built for today’s pace, every new chip or tool that isn’t NVIDIA slams into the same wall. Enter @clattner_llvm (LLVM, Swift, MLIR). After 25+ years re-writing compute, he’s now at @modular_ai building Mojo:…
It was wonderful to get to spend time with the legendary @LisaSu today. She’s such an inspirational leader, it is no wonder that @AMD is on fire! 🔥
Modular is cooking in June, with no plans to slow down! 🔥
Our June community recap is here! A global hackathon, a major video premiere featuring our @AMD partnership, @clattner_llvm on @latentspacepod and at AMD #AdvancingAI 2025, GPU comics, and more! Catch all the updates in the latest community highlights: modular.com/blog/modverse-…
Now on YouTube: @clattner_llvm's full talk from @AMD #AdvancingAI 2025! Learn how Mojo brings together Python’s simplicity and C++ performance to power a next-gen AI software stack. Plus, catch the post-talk Q&A with Chris: youtube.com/watch?v=liR2Pn…
who needs any more under-utilised kernel problems, when you've already got one thanks to @Modular & @clattner_llvm
I'm very excited to partner with SFCompute - Evan and team are phenomenally driven and built a powerful platform for scaling GPU solutions like never before. Combined with Modular's high-performance inference solutions, they're able to deliver incredible TCO advantages! 👇
We've partnered with Modular to create Large Scale Inference (LSI), a new OpenAI-compatible inference service. It's up to 85% cheaper than other offerings & can handle trillion-token scale. We originally created it at the request of a major AI lab to do large scale multimodal…
Dive in to learn how @inworld_ai was able to use Modular's stack to build the world's best speech model: better quality+latency and 20x cheaper running on Blackwell. This was made possible by combining their innovative research with the GenAI-native MAX and Mojo tech.👇🤓
🤯 Building high-performance AI infrastructure doesn’t have to take months! Read about how @modular and @inworld_ai launched a state-of-the-art speech pipeline in under 8 weeks, meeting meeting real-time latency targets and cutting serving costs by 60%. inworld.ai/blog/how-we-ma…
Modular Hack Weekend: GPU Programming Workshop x.com/i/broadcasts/1…
Congratulations to the team at @inworld_ai, setting a new standard for real time speech models! This leap forward makes speech more accessible for products and use-cases everywhere. 🚀 The tech + collaboration powering this is next-level. We'll have more to share soon! 🔥
We just made state-of-the-art TTS 20x more affordable. $5 per million characters. And we're open sourcing the training and modeling code (built on Llama). Because scaling voice AI shouldn't break your budget. Technical Details → Inworld.ai/blog/introduci… Why and how we did it…