Hacker News   << back
code
Bringing Up DeepSeek-V4-Flash on AMD MI300X (fergusfinn.com)
56 points by kkm 3 hours ago | 6 comments

• maCDzP 33 minutes ago

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.

• kkm 31 minutes ago

This is very interesting, planning to write about it?

• mezark 2 hours ago

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

• brcmthrowaway 12 minutes ago

Are you long AMD?

• kkm 2 hours ago

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

• benlm 2 hours ago

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