Excited to share some of my experience in the ML infrastructure world over the past few years!

Working with Microsoft Research to apply int4 acceleration for some of their video workloads has been a real blast. Stay tuned for more details here!

I was never a good systems engineer, so I always avoided the topic of compiling and optimizing ML models. However, as I work with ML on devices, the topic keeps coming up. So I spent the last 3 months learning about ML compilers. Here’s what I learned. huyenchip.com/2021/09/07/a-f…

I was unaware of the large obstacles ahead in scaling up cultured meat production. Fascinating and informative read! engrxiv.org/795su

More fuel to power our mission to enable ML model deployment anywhere, offering choice, automation and performance! Join us today!

And we're live with Day 1 at TVMCon.org! Register for free now to catch some of the great talks today and tomorrow: The latest on Apache TVM and updates on the OctoAI deployment platform!

Some of the coolest work I have seen in a while. Now we just need to compile these continuous neural CAs into genetic regulatory networks for some synbio breakthroughs.

Looks like the movement in computing from vacuum tubes to integrated circuits (see pictures of both setups at end of thread).

Can’t agree more!

Love the user-centric empathy in this thread.

Minimalism for the mind. A fantastic read that I'm now looking forward to digesting for the rest of the weekend. h/t to Arjun Bansal Subtraction, Not Addition, by ibringtraffic andyjohns.substack.com/p/subtraction-…

Let me know if you're at #reMARS and are interested in chatting about deploying ML more easily and efficiently.

Really excited to have Lip-Bu Tan join our board! Can't wait to learn from his extensive experience, and he is such a caring human role model as well.

Excited to see PyTorch 2.0 announced around compiler support and for Apache TVM to be included as a torch.compile and Dynamo upstreamed backend!

Stable diffusion models are fun and usually take a server to run. Today we are happy to share the Web Stable Diffusion project, which brings SD models from Hugging Face and @pytorch to browser clients through WebGPU support. Checkout mlc.ai/web-stable-dif… for our demo!

@OctoML Profiler uses the latest PyTorch 2.0 compiler technology to give developers insight into ML model performance, optimize deep learning applications, and right-size hardware choices without leaving the dev environment! Check it out 👉 hubs.la/Q01K2R2v0

And we're just getting started. Applying int4 optimizations on top of this are looking 🤯🚀

Personal highlights from Claude's snarky AI comedy set.