Jason Knight

Dad of 3 and Co-founder at @OctoAICloud - Enabling developers to build GenAI powered applications.

[Amanda Askell @AmandaAskell]

Personal highlights from Claude's snarky AI comedy set.

[Jason Knight @binarybana]

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

[Jason Knight @binarybana]

@jiayq Looking forward to seeing your results too! AITemplate still wasn’t available as a baseline last I checked as well.

[Jason Knight @binarybana]

@jiayq The baseline compared against here is what you find from hosted SDXL services. We also have <5s results available but at a higher price point if that’s what you’re interested in.

[Jason Knight @binarybana]

@eugeneyan Add another pro to the LoRa list: you can mix multiple LoRa's with user specified weighting.

[PyTorch @PyTorch]

@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 👉 https://t.co/c1hCTyOsNy

[Ruihang Lai @ruihanglai]

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 @huggingface and @pytorch to browser clients through @WebGPU support. Checkout https://t.co/9av529Ol7X for our demo!

[Jason Knight @binarybana]

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

[PyTorch @PyTorch]

We just introduced PyTorch 2.0 at the #PyTorchConference, introducing torch.compile!

Available in the nightlies today, stable release Early March 2023.

Read the full post: https://t.co/DFO0HojkMt

🧵below!

1/5

[Jason Knight @binarybana]

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.

[Jason Knight @binarybana]

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

[Jason Knight @binarybana]

@bernhardsson @brendandburns pushed this concept in “Metaparticle” exploring this concept but it seemed to lose steam. Would love to know why? https://t.co/BVXnIVhfc8

[Jason Knight @binarybana]

@bernhardsson Interesting historical discussion about taking
@deno_land's VM level permissions and extending them to per-library/module. Still NotImplemented, but V8 VM level is definitely better than nothing:

https://t.co/JM8l8gv2ZK

[Jason Knight @binarybana]

Minimalism for the mind. A fantastic read that I'm now looking forward to digesting for the rest of the weekend. h/t to @coffeephoenix

Subtraction, Not Addition, by @ibringtraffic https://t.co/E6ZsVcUaFX

[Jason Knight @binarybana]

@karlhigley Haven’t used it myself, but I wonder if there’s a Feast library component that would serve your need of decoupling your source and sink in a principled way: https://t.co/M66xiW8ThN

[Jason Knight @binarybana]

@NaveenGRao @coffeephoenix @khosra @MosaicML It’s good to know it gets easier the second time around! 😅

[Jason Knight @binarybana]

Love the user-centric empathy in this thread.

[olivier giroux @__simt__]

I'm bored being funemployed over here.

Anybody want to ask me something? About GPUs, architecture, career advice? Fire away.

[Jason Knight @binarybana]

Can’t agree more!

[Jason Knight @binarybana]

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

[Emma J Chory @chorye]

Best way to ring in the new year! @erika_alden_d and I are excited to share our story on high-throughput continuous evolution, available now in @naturemethods. We've added a ton to the story since the preprint, and hope you'll check it out! thread 1/n... https://t.co/e76mfVIlNN

[Jason Knight @binarybana]

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.

[Aleksa Gordić (水平问题) @gordic_aleksa]

https://t.co/z17Z5nfEjb <- one and only Distill. A nice introduction to how neural CA works and how it may be a potentially useful model of morphogenesis and regeneration processes in developmental biology.

@zzznah

2/

[Jason Knight @binarybana]

@migueldeicaza @petewarden @roeschinc Correct, TVM has pretty sophisticated/flexible fusion capabilities. Though there are opens around mixing custom TVM ops into the rest of your framework, though we can always compile the entire network at the end of the day to get around that. :)