# How can I use vllm with cuda 12.9

**URL:** <https://discuss.vllm.ai/t/how-can-i-use-vllm-with-cuda-12-9/2765>\
**Category:** General\
**Created:** [July 8, 2026, 8:11am UTC](https://discuss.vllm.ai/t/how-can-i-use-vllm-with-cuda-12-9/2765 "2026-07-08T08:11:06Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![helloqiua](https://yyz2.discourse-cdn.com/flex036/user_avatar/discuss.vllm.ai/helloqiua/32/1547_2.png) [@helloqiua](https://discuss.vllm.ai/u/helloqiua)\
**Post date:** [July 10, 2026, 2:24am UTC](https://discuss.vllm.ai/t/how-can-i-use-vllm-with-cuda-12-9/2765/5 "2026-07-10T02:24:17Z")

</div>

I change to use 0.22.0 to solve my problem. After comparing our solutions, the only difference between yours and mine is that you installed the CUDA Toolkit. Will the setup work successfully once this toolkit is installed?

---

_[View the full topic](https://discuss.vllm.ai/t/how-can-i-use-vllm-with-cuda-12-9/2765)._