{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"flash-attention","owner":"ai-compiler-study","isFork":true,"description":"Fast and memory-efficient exact attention","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1227,"license":"BSD 3-Clause \"New\" or \"Revised\" License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-18T15:19:56.718Z"}},{"type":"Public","name":"triton-kernels","owner":"ai-compiler-study","isFork":false,"description":"Triton kernels for SD3 and Flux","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-18T02:43:54.230Z"}},{"type":"Public","name":"flux","owner":"ai-compiler-study","isFork":true,"description":"Official inference repo for FLUX.1 models","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":978,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-10T15:06:30.486Z"}},{"type":"Public","name":"kernels","owner":"ai-compiler-study","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":11,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-09T14:07:00.342Z"}},{"type":"Public","name":"nexfort","owner":"ai-compiler-study","isFork":false,"description":"OneDiff compiler infrastructure using torch Inductor","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-06T15:12:21.413Z"}},{"type":"Public","name":"xDiT","owner":"ai-compiler-study","isFork":true,"description":"xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) on multi-GPU Clusters","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":41,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-30T10:45:33.265Z"}},{"type":"Public","name":"quanto","owner":"ai-compiler-study","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-14T12:30:10.598Z"}},{"type":"Public","name":"minRF-ONNX","owner":"ai-compiler-study","isFork":true,"description":"Minimal implementation of scalable rectified flow transformers, based on SD3's approach","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":5,"forksCount":28,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-27T14:40:22.694Z"}},{"type":"Public","name":"quant_dit_models","owner":"ai-compiler-study","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-25T14:45:11.327Z"}},{"type":"Public","name":"cutlass-kernels","owner":"ai-compiler-study","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Cuda","color":"#3A4E3A"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":27,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-11T22:03:17.724Z"}},{"type":"Public","name":"unet.cu","owner":"ai-compiler-study","isFork":true,"description":"UNet diffusion model in pure CUDA","allTopics":[],"primaryLanguage":{"name":"Cuda","color":"#3A4E3A"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":28,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-28T18:12:58.352Z"}}],"repositoryCount":11,"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":"ai-compiler-study repositories"}