Michael Dunn-OConnor

[Michael Dunn-OConnor @dunn_oconnor]

@Modular An excellent talk from Billy! Really clear examples of what makes Mojo special

[Modular @Modular]

Haven't had time to explore Mojo 1.0 beta yet? @InfoWorld published a piece on Mojo 1.0 that will get you up to speed on language basics, metaprogramming, Python interop, GPU support, and more:

https://t.co/NGtpTd4FHz

[Michael Dunn-OConnor @dunn_oconnor]

@Modular I learned a lot from sitting down with Kyle and hearing his guided tour of inference serving. I'm glad we can share this with the MAX community!

[Michael Dunn-OConnor @dunn_oconnor]

@ScioNos_ @davidrobertson @codewithimanshu @Modular @UnslothAI More on the plan to open-source the Mojo compiler here:
https://t.co/GpSOEni5Pp

[Modular @Modular]

Zero GPU experience. Outperformed & improved @UnslothAI's CUDA kernel😱 @davidrobertson on what happens when you don't have to fight the language to get performance🔥
https://t.co/7q0sGxI6nY

[Modular @Modular]

🔥 New Series! Learning GPU programming through Mojo puzzles - on an Apple M4! No expensive data center GPUs needed. No CUDA C++ complexity. Just Python-like syntax with systems performance.

First video just dropped: https://t.co/MI0BzfBuL0

#Mojo #GPUProgramming #AppleSilicon

[Michael Dunn-OConnor @dunn_oconnor]

@verma_mle @Modular Yes! Full list of compatible GPUs here: https://t.co/FiDQbl9ZEV

[Mehdi Amini @JokerEph]

7th edition of the #MLIR workshop alongside the #LLVM conference, another great lineup of talks: impressive work all around!
127 people in the audience, nice turnaround :)
Here #Mojo GPU programming.

[Modular @Modular]

We raised $250M to accelerate building AI's unified compute layer! 🔥 We’re now powering trillions of tokens, making AI workloads 4x faster 🚀 and 2.5x cheaper ⬇️ for our customers, and welcomed 10K’s of new developers 👩🏼‍💻. We're excited for the future!

[Modular @Modular]

We're thrilled to announce Modular Platform 25.6 🚀
Our biggest step yet toward a unified compute layer for AI.

• Peak performance on NVIDIA Blackwell & AMD MI355X
• Mojo on Apple, AMD & NVIDIA consumer GPUs

https://t.co/rJc1KjIsx9

[Modular @Modular]

Part 4 of "Matrix Multiplication on Blackwell" is here! It continues our epic journey of describing how Modular implemented the fastest B200 matmul in the industry, revealing the techniques to achieve 1772 TFLOPs, exceeding that of the current SOTA.

https://t.co/jhBeJBvmuc

[Chris Lattner @clattner_llvm]

Triton is nice if you want to get something onto a GPU but don't need full performance/TCO. However, if you want peak perf or other HW, then Mojo🔥 could be a better fit. I'm glad OpenAI folk are acknowledging this publicly, but I wrote about it here:
https://t.co/dzGlAUapOY

[Modular @Modular]

ssshh... 🤫 @AMD Mi355X... now available in nightlies.

[Modular @Modular]

Part 3 of "Matrix Multiplication on Blackwell" is here! It continues our epic journey of describing how Modular implemented the fastest B200 matmul in the industry, revealing the techniques to go from 16% to 85% of SOTA

https://t.co/W8iahcB5Ct

[Modular @Modular]

Learn how @inworld_ai teamed up with @Modular and @OracleCloud to unlock hardware optionality across Nvidia and AMD GPUs for their groundbreaking TTS models, cutting total cost of model ownership by 70%.