Dark Hacker News
new
|
best
|
ask
|
show
|
jobs
NicoConstant | Dark Hacker News
user:
NicoConstant
created:
March 13, 2026
karma:
42
submissions
comments
1.
Real-time LLM Inference on Standard GPUs: 3k tokens/s per request
(blog.kog.ai)
121 points
by
NicoConstant
6 hours ago
|
60 comments
2.
Kog AI – Building a Real-Time Inference Stack on AMD Instinct GPUs [video]
(youtube.com)
8 points
by
NicoConstant
14 days ago
|
0 comments