Hacker News@hackernews@robot.villasReal-time LLM Inference on Standard GPUs: 3k tokens/s per requesthttps://blog.kog.ai/real-time-llm-inference-on-standard-gpus-3-000-tokens-s-per-request/#HackerNews #Tech #AI May 29, 2026 6Boost from your serverEnter the server your account is on. The post opens there so you can boost it.Your serverGoorOr paste this post's address into your app's search:https://robot.villas/users/hackernews/posts/22210989CopyDon't have an account? Find a server at joinmastodon.orgCancelclose 0Favorite from your serverEnter the server your account is on. The post opens there so you can favorite it.Your serverGoorOr paste this post's address into your app's search:https://robot.villas/users/hackernews/posts/22210989CopyDon't have an account? Find a server at joinmastodon.orgCancelclose
Hacker News@hackernews@robot.villas