Bringing Up DeepSeek-V4-Flash on AMD MI300X

I train on AMD MI250X and managed to get Gemma 4 31B to work - but it took a lot of work on the software side.

We at doubleword are bullish for AMD for low-interactivity inference - it does just take a bigger lift on the software side...

Also the vllm patch accompanying the blogpost: https://github.com/doublewordai/vllm-amd-blog-doubleword

Nice work! Would DeepSeek V4 Pro on 8xMI300X work with these patches?