{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"vllm","owner":"vllm-project","isFork":false,"description":"A high-throughput and memory-efficient inference and serving engine for LLMs","allTopics":["amd","cuda","inference","pytorch","transformer","llama","gpt","rocm","model-serving","tpu","mlops","xpu","llm","inferentia","llmops","llm-serving","trainium"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":304,"issueCount":984,"starsCount":21866,"forksCount":3082,"license":"Apache License 2.0","participation":[19,6,14,8,12,5,5,14,11,20,18,21,21,8,16,14,1,21,10,17,23,26,19,39,30,6,11,17,21,24,28,15,24,27,33,31,49,41,70,42,53,43,64,66,47,49,38,48,65,92,73,79],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-30T11:50:35.087Z"}},{"type":"Public","name":"llm-compressor","owner":"vllm-project","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":0,"starsCount":36,"forksCount":1,"license":"Apache License 2.0","participation":[4,14,7,7,2,2,1,2,1,1,6,4,2,11,5,14,6,12,6,15,11,9,4,11,8,1,0,10,13,21,14,5,20,15,11,13,6,7,8,9,10,2,11,2,8,5,9,9,4,6,19,41],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-28T21:22:09.373Z"}},{"type":"Public","name":"flash-attention","owner":"vllm-project","isFork":true,"description":"Fast and memory-efficient exact attention","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":5,"forksCount":1043,"license":"BSD 3-Clause \"New\" or \"Revised\" License","participation":[9,3,14,19,5,5,25,17,17,24,10,15,7,5,3,0,2,0,1,2,6,6,0,0,14,8,5,5,8,20,8,7,12,6,4,0,5,1,12,1,4,0,4,0,7,0,6,3,2,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-07T01:53:57.411Z"}},{"type":"Public archive","name":"vllm-nccl","owner":"vllm-project","isFork":false,"description":"Manages vllm-nccl dependency","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":16,"forksCount":2,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,9,1,1,2,0,0,0,0,0,1,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-03T22:00:55.924Z"}},{"type":"Public","name":"dashboard","owner":"vllm-project","isFork":false,"description":"vLLM performance dashboard","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":12,"forksCount":3,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,15,6,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-26T06:13:47.853Z"}}],"repositoryCount":5,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}