N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
Bringing Up DeepSeek-V4-Flash on AMD MI300X
(
fergusfinn.com
)
68 points by
kkm
5 hours ago
|
6 comments
add comment
Rendered at 22:52:35 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
maCDzP 2 hours 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 2 hours ago
[-]
This is very interesting, planning to write about it?
mezark 3 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 2 hours ago
[-]
Are you long AMD?
kkm 3 hours ago
[-]
Also the vllm patch accompanying the blogpost:
https://github.com/doublewordai/vllm-amd-blog-doubleword
benlm 3 hours ago
[-]
Nice work! Would DeepSeek V4 Pro on 8xMI300X work with these patches?