Dark Hacker News
new
|
best
|
ask
|
show
|
jobs
Bringing Up DeepSeek-V4-Flash on AMD MI300X | Dark Hacker News
Bringing Up DeepSeek-V4-Flash on AMD MI300X
(fergusfinn.com)
55 points
by
kkm
3 hours ago
| 6 comments
maCDzP
25 minutes ago
|
next
[−]
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
23 minutes ago
|
parent
|
next
[−]
This is very interesting, planning to write about it?
mezark
1 hour ago
|
next
[−]
We at doubleword are bullish for AMD for low-interactivity inference - it does just take a bigger lift on the software side...
brcmthrowaway
4 minutes ago
|
parent
|
next
[−]
Are you long AMD?
kkm
1 hour ago
|
next
[−]
Also the vllm patch accompanying the blogpost:
https://github.com/doublewordai/vllm-amd-blog-doubleword
benlm
1 hour ago
|
next
[−]
Nice work! Would DeepSeek V4 Pro on 8xMI300X work with these patches?