{"author":"shubham0204","children":[{"author":"shubham0204","children":[],"created_at":"2026-11-14T02:05:37.000Z","created_at_i":1794621937,"id":50492878,"options":[],"parent_id":50492877,"points":null,"story_id":50492877,"text":"The llama.cpp team at HuggingFace announced that the framework has reached a stable version of 1.0, spending 3.5 years in development since its inception. This version will have stabilized APIs and follow semantic versioning (major-minor-patch) here after.","title":null,"type":"comment","url":null},{"author":"cobychapple","children":[{"author":"shubham0204","children":[],"created_at":"2026-11-14T05:55:56.000Z","created_at_i":1794635756,"id":50494419,"options":[],"parent_id":50493082,"points":null,"story_id":50492877,"text":"Yes, libggml and libllama also went 1.0.","title":null,"type":"comment","url":null}],"created_at":"2026-11-14T02:30:32.000Z","created_at_i":1794623432,"id":50493082,"options":[],"parent_id":50492877,"points":null,"story_id":50492877,"text":"Looks like ggml went 1.0 too: <a href=\"https:&#x2F;&#x2F;github.com&#x2F;ggml-org&#x2F;ggml&#x2F;releases&#x2F;tag&#x2F;v1.0.0\" rel=\"nofollow\">https:&#x2F;&#x2F;github.com&#x2F;ggml-org&#x2F;ggml&#x2F;releases&#x2F;tag&#x2F;v1.0.0</a>","title":null,"type":"comment","url":null},{"author":"ChrisArchitect","children":[],"created_at":"2026-11-14T18:40:32.000Z","created_at_i":1794681632,"id":50499571,"options":[],"parent_id":50492877,"points":null,"story_id":50492877,"text":"Related:<p><i>Ggml v1.0.0</i><p><a href=\"https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=50493062\">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=50493062</a>","title":null,"type":"comment","url":null}],"created_at":"2026-11-14T02:05:37.000Z","created_at_i":1794621937,"id":50492877,"options":[],"parent_id":null,"points":26,"story_id":50492877,"text":null,"title":"Llama.cpp hits v1.0 with a native app for macOS","type":"story","url":"https://huggingface.co/blog/ggml-org/llama-cpp-v1"}
