Woosuk Kwon

@woosuk_k

@inferact | @vllm_project | prev: PhD @Berkeley_EECS

woosuk.me

Joined April 2023

Replies Reposts Media

Pinned
Woosuk Kwon
@woosuk_k
Jan 22
Today, we're proud to announce @inferact, a startup founded by creators and core maintainers of @vllm_project, the most popular open-source LLM inference engine. Our mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper
183
Woosuk Kwon
@woosuk_k
Sep 8
TPU is an interesting chip with enormous potential. Shoutout to @googlecloud for all great work and support!
Dylan Patel
@dylan522p
Sep 7
We are excited to bring the first open benchmarking of Google's TPUs to the world Running every day, on many models + scenarios $/token is better than B200 and B300 Huge shout-out to Google @inferact and the InferenceX team at SemiAnalysis to this effort that's taken many months
4
Woosuk Kwon
@woosuk_k
Aug 11
We are hiring! Come join us and advance the frontier of AI inference!
SemiAnalysis
@SemiAnalysis_
Aug 10
The @vllm_project maintainers at @inferact 🚀 are some of the most cracked engineers in the world. They’re building one of the inference engines that powers much of the world’s intelligence—and doing so with remarkable dedication, kindness, and hard work.
5
Woosuk Kwon
@woosuk_k
Aug 4
See you at the conference!
vLLM
@vllm_project
Aug 4
The vLLM Conference is coming up in 3 weeks! 🎉 Come learn about the current state and future of AI inference, Aug 24–26 in San Francisco 🌉, hosted by @inferact at @anyscalecompute Ray Summit. We'll have speakers from Inferact, NVIDIA, AMD, Google TPU, Anyscale, PyTorch, Meta,
2
Woosuk Kwon
@woosuk_k
Jul 30
Great to see the model small enough to run on a single (!) B300. It might be the best model in its size class! Have fun 🫡
vLLM
@vllm_project
Jul 30
🎉 Congrats to @thinkymachines on Inkling-Small-- live with Day 0 vLLM support! 276B total parameters with 12B active, native text, image, and audio input, and a 1M-token context window. Open weights, built for agentic and tool-use systems, coding assistants, and RAG. Running
2