🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Pleased to be investing in MatX, building AI chips with breakthrough capability: bloomberg.com/news/articles/…

Given exponential increase in training costs, compute multipliers might become the most coveted secrets on earth. Some of those will be in torch.nn; many will be in silicon.

Daniel Gross very interesting observation re: aggregation / disaggregation dynamics for startups: "Inside of Google, there were lots of people who wanted changes to the chips for all sorts of things, and it was difficult to focus just on LLMs"

We’re releasing seqax, a research-focused LLM codebase that is simple, explicit, and performs well on up to ~100 GPUs/TPUs. Everything you need to edit, from the math, to parallelism, to memory footprint, is all there in 500 lines of JAX code. 🧵 github.com/MatX-inc/seqax

MatX will be at MLSys. Come join us at our After Hours in Santa Clara to talk about chips, compilers, partitioning, and optimizing ML models for future hardware. Many of us will be there, including me and @mikegunter_. Tuesday May 14th at 4pm, see matx.com/meetmatx.

NEW ODD LOTS: Two Veteran Chip Designers Have A Plan To Take On Nvidia Tracy Alloway and I talked to Reiner Pope and Mike Gunter, both formerly of Alphabet, about their new company MatX that's aiming to build the ultimate semiconductor just for LLMs bloomberg.com/news/articles/…

I really enjoyed talking about the process and business of semiconductor design with Tracy Alloway and Joe Weisenthal on the Odd Lots podcast. Joe and Tracy were wonderful hosts: They put me at ease and guided the conversation with the lightest of touch. We talked about what doing

1. Breakdown of DeepSeek V3 efficiency vs Llama 3: - Better: 11x fewer FLOPs per token, thanks to MoE [37B vs 405B activated params] - Better: 2x faster numerics [fp8 vs bf16 training] - Worse: 0.5x flops utilization [16% vs 33% end-to-end MFU*] - Neutral: similar hardware

MatX is designing chips and systems to 10x the computing power for the world’s largest AI workloads. Today, we are pleased to announce the closing of a >$100M Series A funding round led by Spark Capital, with participation from Jane Street, Daniel Gross and Nat Friedman,

MatX hardware will maximize intelligence per dollar for the world’s largest models. We are a team of 50+ and growing quickly. If you are passionate about building the best chips for LLMs, consider joining us. matx.com/jobs

Excited to say I joined MatX late last year! The team is exceptionally thoughtful and the problems are both difficult and fun: from µarch, compilers, and models, to the systems we are building.

I'll be in Toronto and Waterloo over the next week, I'd love to chat and tell you a bit more about what we're doing at MatX (and say hi); please feel free to reach out!

Join us in Waterloo to chat systems at Whoopsie Daisy Drinks: lu.ma/matx-waterloo