2026-10-20 · America/Los_Angeles · 社区动态 · #7

Open models. Open kernels. Open inference

https://x.com/deepseek_ai/status/2112476496283775135 https://github.com/deepseek-ai/deepseek-recipe https://github.com/deepseek-ai/DeepInfer/blob/main/doc/inference_deployment_qa.md "A single cluster currently serves 155 trillion tokens per day, with overall revenue of US$38 per GPU-hour (at valley pricing)."

热度 50.6 / 100；排名与评分保留该期记录。