# Introducing vLLM-Tune — Kernel tuning CLI for vLLM on DGX Spark

**URL:** <https://forums.developer.nvidia.com/t/introducing-vllm-tune-kernel-tuning-cli-for-vllm-on-dgx-spark/368039>\
**Category:** DGX Spark / GB10 Projects\
**Tags:** llama\
**Created:** [April 27, 2026, 1:23pm UTC](https://forums.developer.nvidia.com/t/introducing-vllm-tune-kernel-tuning-cli-for-vllm-on-dgx-spark/368039 "2026-04-27T13:23:48Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![azampatti](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/azampatti/32/503643_2.png) [@azampatti](https://forums.developer.nvidia.com/u/azampatti)\
**Post date:** [April 29, 2026, 5:14am UTC](https://forums.developer.nvidia.com/t/introducing-vllm-tune-kernel-tuning-cli-for-vllm-on-dgx-spark/368039/9 "2026-04-29T05:14:15Z")

</div>

Well… Just discover this today and here’s my before/after of my Qwen3.6-35B-A3B-FP8 with DFlash before and after:

 ![image](https://global.discourse-cdn.com/nvidia/original/4X/5/0/c/50cbb6d339a693f2800f89749b6c2c254f417de9.png)

After vLLM Tune:

 ![image](https://global.discourse-cdn.com/nvidia/original/4X/7/3/e/73e9338224d362d7da55cde88df16b3b4ee28f7b.png)

It’s like way more consistent across different scenarios. I like it!

---

_[View the full topic](https://forums.developer.nvidia.com/t/introducing-vllm-tune-kernel-tuning-cli-for-vllm-on-dgx-spark/368039)._