Bringing Up DeepSeek-V4-Flash on AMD MI300X
fergusfinn.com
Bringing Up DeepSeek-V4-Flash on AMD MI300X
1–10 of 29 posts
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#2Nice work! Would DeepSeek V4 Pro on 8xMI300X work with these patches?
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#3Also the vllm patch accompanying the blogpost:
https://github.com/doublewordai/vllm-amd-blog-doubleword
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#4We at doubleword are bullish for AMD for low-interactivity inference - it does just take a bigger lift on the software side...
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#5I train on AMD MI250X and managed to get Gemma 4 31B to work - but it took a lot of work on the software side.
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#6I train on AMD MI250X and managed to get Gemma 4 31B to work - but it took a lot of work on the software side.
This is very interesting, planning to write about it?
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#7We at doubleword are bullish for AMD for low-interactivity inference - it does just take a bigger lift on the software side...
Are you long AMD?
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#8Nice work and thanks for being a customer.
(CEO Hot Aisle)
Re: Bringing Up DeepSeek-V4-Flash on AMD MI300X
#9[flagged]