3 points, 0 comments on Hacker News
2 points, 1 comments on Hacker News
If you run vLLM with --kv-cache-dtype fp8 on a DeepSeek-family (MLA) model and your GPU is a GB10, an RTX PRO 6000, or any workstation or consumer Blackwell card, there is a decent chance the engine dies on startup with: triton. runtime. errors.
OpenAI’s new ChatGPT Admin plugin lets workspace admins manage users and permissions, analyze usage, and build reports directly from a conversation. Here are the details.
1 points, 0 comments on Hacker News
1 points, 1 comments on Hacker News