Luis Ceze’s Post

View profile for Luis Ceze, graphic

VP at NVIDIA & Lazowska Endowed Professor at University of Washington

It's stunning to see the progress of open source foundation models in the past year - you've probably heard a lot about that. But I would like to point out that the progress in open source AI software infrastructure also made incredible progress. Just to name a (very) few: vLLM for LLM serving, MLC-LLM (off-shoot of Apache TVM) for portable deployment across a wide range of cloud and edge hardware, LoRAX and Punica for multiplexed fined-tuned model inference, Deepspeed for training, etc. There is a great symbiosis happening in open source model and infrastructure innovation, and I suspect we will see even more in 2024. Please name some of your favorite open source AI infra projects.

Meryem Arik

Co-founder/CEO at TitanML | Secure Enterprise GenAI | Forbes 30 Under 30

10mo

We love the Triton language - we use it extensively in Titan Takeoff Inference Server. https://github.com/openai/triton It allows us to be super flexible when it comes to adding new models & support non-nvidia hardware

Travis Addair

Co-Founder & CTO at Predibase

10mo

Couldn’t agree more! Thanks for the LoRAX shoutout, and congrats on MLC-LLM and Punica.

Jon Turow

Builder. Madrona Partner. Ex Amazon AWS.

10mo

QLoRA!

Andrew Aikawa

Co-founder, CTO | YC S23 | We're your personal GPU cloud infra team. We👷♂️ build high performance GPU management infrastructure in less than a day

10mo

SkyPilot

See more comments

To view or add a comment, sign in

Explore topics