Building the future of inference
- PinnedProud to host the first vLLM Conference at Ray Summit, Aug 2426 in SF We're bringing the community together to talk about what's next: Building and scaling AI in production Deploying vLLM to run inference across your own cloud and hardware What open source means Show moreAnnouncing the first-ever vLLM Conference hosted by @inferact at Ray Summit, Aug 2426 in San Francisco This is where we'll get into the work pushing open, high-performance inference forward, such as: Where the vLLM roadmap is headed Getting the most out of Show more1299.6K
- Teaming up with @digitalocean & @nvidia for a happy hour on Aug 26 as the vLLM Conference wraps Come say hi! do.co/4g0oAhEWere closing out Ray Summit + the vLLM Conference with our happy hour, hosted with @nvidia & @inferact. Lightning talks, live demos, cold drinks, and a room full of builders who are optimizing intelligence per dollar. RSVP today. do.co/4g0oAhE23172.5K
- Proud to co-host this one with the @vllm_project community and the @nvidia Dynamo team In SF for vLLM conference week Aug 24-26? Come talk inference optimization, distributed serving, and everything that breaks at scale. We'd love to meet youWe're co-hosting a @vllm_project x @nvidia Dynamo Meetup during vLLM Conference week in San Francisco Tech talks on serving LLMs efficiently at scale + food, drinks, and the inference community all in one room Aug 24, 69pm PT Space is limited RSVP: Show more2222.6K
- With @inferact, @vllm_project is now officially verified by @Kimi_Moonshot to serve Kimi K3 with full accuracy, according to the Kimi Vendor Verifier. As the leading inference engine, vLLM delivers best results across vision, 1M context, and agentic coding; with prod quality.4136535K
- Our Co-founder and CEO @simon_mo_ sat down with @BornsteinMatt and @VirtualElena at @a16z to talk about how vLLM runs on 500K+ GPUs at any given moment, what it takes to run open models in production, and the mission behind Inferact. Tune in belowvLLM runs on half a million GPUs at any given moment. Most people have never heard of it. Simon Mo, co-founder and CEO of @inferact and lead maintainer of vLLM, sits down with a16zs Matt Bornstein and Elena Burger to discuss what it takes to actually run open models in Show more6233.5K
![[user avatar]](https://pbs.twimg.com/profile_images/2014219818292117505/paUacyDa_400x400.jpg){kind=link}
![[user avatar]](https://pbs.twimg.com/profile_images/2014219818292117505/paUacyDa_normal.jpg){kind=link}
![[user avatar]](https://pbs.twimg.com/profile_images/1774187681746182144/N_5NJ8B1_normal.jpg){kind=link}
![[user avatar]](https://pbs.twimg.com/profile_images/2050225101212123136/2fGuxzWh_normal.jpg){kind=link}
![[user avatar]](https://pbs.twimg.com/profile_images/1919488160125616128/QAZXTMEj_normal.png){kind=link}
![[]](https://pbs.twimg.com/amplify_video_thumb/2085428883659407360/img/UB5ksyKB-jihsm2P.jpg){kind=link}