{"full_name":"GeeeekExplorer/nano-vllm","owner":"GeeeekExplorer","name":"nano-vllm","shard":"1","url":"https://github.com/GeeeekExplorer/nano-vllm","description":"Nano vLLM","homepage":"","topics":["inference","llm","pytorch","transformer","deep-learning","nlp"],"tag_pages":["deep-learning","inference","llm","nlp","pytorch","transformer"],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/38156925?v=4","created_at":"2025-06-09T16:22:14Z","pushed_at":"2026-04-26T05:10:12Z","metrics":{"stars":16439,"forks":2863,"watchers":86,"issues":112,"prs":182,"releases":0,"issues_open":31,"issues_closed":81,"prs_open":80,"prs_closed":82,"prs_merged":20,"discussions":0},"growth":{"day":{"stars":12,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[16385,16388,16397,16404,16420,16427,16439],"forks":[2849,2857,2860,2860,2861,2863,2863],"watchers":[null,86,86,86,86,86,86],"issues_open":[null,31,31,31,31,31,31],"prs_open":[null,80,80,80,80,80,80]},"boards":{},"same_owner":[],"issues":[{"number":167,"title":"rope argument inconsistent","comments":9,"created_at":"2026-01-28T01:27:36Z"},{"number":25,"title":"How did this job achieve such excellent performance?","comments":8,"created_at":"2025-06-18T09:18:34Z"},{"number":220,"title":"[Feature Request] Support weightless RMSNorm (for FlashNorm weight folding trick)","comments":5,"created_at":"2026-04-29T00:14:29Z"},{"number":73,"title":"Support for Chunked Prefill of new seqs while decoding old seqs","comments":5,"created_at":"2025-07-08T02:03:34Z"},{"number":48,"title":"Implement support for Qwen2.5vl","comments":5,"created_at":"2025-06-24T23:40:47Z"},{"number":240,"title":"[Bug] may_append allocates new block one token too late, causing KV cache write to unallocated block","comments":2,"created_at":"2026-06-08T13:11:32Z"},{"number":189,"title":"Qwen models initialization fails with TypeError: unhashable type: 'dict' and AssertionError due to rope_scaling","comments":2,"created_at":"2026-03-23T02:35:44Z"},{"number":165,"title":"🚀 Introducing Nano-vLLM-v1 – A Lightweight, Re-engineered Nano vLLM Implementation with vLLM v1 Scheduler and Chunked Prefill","comments":2,"created_at":"2026-01-25T13:10:41Z"}],"discussions":[],"latest_release":null,"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}