{"full_name":"FMInference/FlexLLMGen","owner":"FMInference","name":"FlexLLMGen","url":"https://github.com/FMInference/FlexLLMGen","description":"Running large language models on a single GPU for throughput-oriented scenarios.","homepage":"","topics":[],"language":"Python","license":null,"avatar":null,"created_at":"2023-02-15T21:18:53Z","pushed_at":"2024-10-28T03:05:41Z","metrics":{"stars":9340,"forks":588,"watchers":null,"issues":null,"prs":null,"releases":null,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":null},"growth":{},"history":{"dates":["2026-11-10"],"stars":[9340],"forks":[588],"watchers":[null],"issues_open":[null],"prs_open":[null]},"boards":{},"same_owner":[],"issues":[],"discussions":[],"latest_release":null,"readme":false,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}