Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
61.
Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs (news.ycombinator.com)
62.
Positron believes it has found the secret to take on Nvidia in AI inference chips — here’s how it could benefit enterprises (venturebeat.com)
63.
My favorite use-case for AI is writing logs (news.ycombinator.com)
64.
LLM Inference Handbook (news.ycombinator.com)
65.
I extracted the safety filters from Apple Intelligence models (news.ycombinator.com)
66.
Tools: Code Is All You Need (news.ycombinator.com)
67.
The inference trap: How cloud providers are eating your AI margins (venturebeat.com)
68.
How runtime attacks turn profitable AI into budget black holes (venturebeat.com)
69.
Nvidia’s ‘AI Factory’ narrative faces reality check as inference wars expose 70% margins (venturebeat.com)
70.
Groq just made Hugging Face way faster — and it’s coming for AWS and Google (venturebeat.com)
71.
OpenInfer raises $8M for AI inference at the edge (venturebeat.com)
Today's top topics: apple openai google amazon zdnet meta anthropic android authority chatgpt microsoft
View all today's topics →