DeepSeek V4 Flash on a Single AMD MI300X
(news.ycombinator.com)
1.
2.
Bringing Up DeepSeek-V4-Flash on AMD MI300X
(news.ycombinator.com)
3.
Real-time LLM Inference on Standard GPUs: 3k tokens/s per request
(news.ycombinator.com)
4.
ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math
(news.ycombinator.com)
5.
Why isn't AMD's MI300X competitive?
(news.ycombinator.com)
6.
7.
Is a $30,000 GPU Good at Password Cracking?
(bleepingcomputer.com)
Today's top topics:
apple
openai
anthropic
iphone 18 pro
iphone duo
google
ios 27
ai safety
apple watch series 12
iphone