{"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","topicNames":["amd","cuda","inference","pytorch","transformer","llama","gpt","rocm","model-serving","mlops"],"topicsNotShown":5,"allTopics":["amd","cuda","inference","pytorch","transformer","llama","gpt","rocm","model-serving","mlops","llm","inferentia","llmops","llm-serving","trainium"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":243,"issueCount":853,"starsCount":19881,"forksCount":2683,"license":"Apache License 2.0","participation":[5,8,2,23,18,17,10,11,13,11,5,5,13,8,15,22,20,18,18,11,17,4,18,8,8,35,13,26,37,37,8,7,11,20,26,30,21,18,24,28,33,34,57,47,58,44,49,57,68,52,48,50],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-23T06:13:03.943Z"}},{"type":"Public","name":"flash-attention","owner":"vllm-project","isFork":true,"description":"Fast and memory-efficient exact attention","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":2,"forksCount":984,"license":"BSD 3-Clause \"New\" or \"Revised\" License","participation":[11,19,3,0,0,6,3,12,19,10,0,19,17,25,25,9,12,13,3,4,1,2,0,0,3,6,5,1,0,6,16,1,6,11,19,9,1,18,6,2,2,0,6,3,9,5,0,4,0,7,0,6],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-22T22:53:28.236Z"}},{"type":"Public","name":"vllm-nccl","owner":"vllm-project","isFork":false,"description":"Manages vllm-nccl dependency","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":12,"forksCount":2,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,9,1,1,2,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-01T20:54:28.924Z"}},{"type":"Public","name":"dashboard","owner":"vllm-project","isFork":false,"description":"vLLM performance dashboard","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":12,"forksCount":3,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,20,1,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-26T06:13:47.853Z"}}],"repositoryCount":4,"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"}