{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":653379923,"defaultBranch":"master","name":"llama.cpp","ownerLogin":"DavidAlphaFox","currentUserCanPush":false,"isFork":true,"isEmpty":false,"createdAt":"2023-06-14T00:21:06.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/1024948?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1686702072.980048","currentOid":""},"activityList":{"items":[{"before":"e00b4a8f816ebc45b98a46e5f5231359b9a017e0","after":"0541f06296753dbc59a57379eb54cec865a4c9f9","ref":"refs/heads/master","pushedAt":"2024-05-31T04:44:54.000Z","pushType":"push","commitsCount":298,"pusher":{"login":"DavidAlphaFox","name":"David.Gao","path":"/DavidAlphaFox","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1024948?s=80&v=4"},"commit":{"message":"[no ci] docs: add aikit to readme (#7650)\n\nSigned-off-by: Sertac Ozercan <sozercan@gmail.com>","shortMessageHtmlLink":"[no ci] docs: add aikit to readme (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2326242318\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7650\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7650/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7650\">ggerganov#7650</a>)"}},{"before":"8228b66dbc16290c5cbd70e80ab47c068e2569d8","after":"e00b4a8f816ebc45b98a46e5f5231359b9a017e0","ref":"refs/heads/master","pushedAt":"2024-04-29T04:49:00.000Z","pushType":"push","commitsCount":108,"pusher":{"login":"DavidAlphaFox","name":"David.Gao","path":"/DavidAlphaFox","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1024948?s=80&v=4"},"commit":{"message":"Fix more int overflow during quant (PPL/CUDA). (#6563)\n\n* Fix more int overflow during quant.\r\n\r\n* Fix some more int overflow in softmax.\r\n\r\n* Revert back to int64_t.","shortMessageHtmlLink":"Fix more int overflow during quant (PPL/CUDA). (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2233431130\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/6563\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/6563/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/6563\">ggerganov#6563</a>)"}},{"before":"940efa95fec0b8a98c226a889d2ad839dfeeae0d","after":"8228b66dbc16290c5cbd70e80ab47c068e2569d8","ref":"refs/heads/master","pushedAt":"2024-04-11T05:51:08.000Z","pushType":"push","commitsCount":1264,"pusher":{"login":"DavidAlphaFox","name":"David.Gao","path":"/DavidAlphaFox","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1024948?s=80&v=4"},"commit":{"message":"gguf : add option to not check tensor data (#6582)\n\nThis commit adds an option to the gguf example to not check the tensor\r\ndata.\r\n\r\nThe motivation for this is that it can be nice to use the gguf tool to\r\nread other .gguf files that were not created by the gguf tool.\r\n\r\nSigned-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>","shortMessageHtmlLink":"gguf : add option to not check tensor data (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2234912794\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/6582\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/6582/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/6582\">ggerganov#6582</a>)"}},{"before":"89e89599fd095172f8d67903b5e227467420f036","after":"940efa95fec0b8a98c226a889d2ad839dfeeae0d","ref":"refs/heads/master","pushedAt":"2023-10-17T00:36:59.000Z","pushType":"push","commitsCount":168,"pusher":{"login":"DavidAlphaFox","name":"David.Gao","path":"/DavidAlphaFox","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1024948?s=80&v=4"},"commit":{"message":"llava : fix tokenization to not add bos between image embeddings and user prompt (#3645)\n\n* llava : fix tokenization to not add bos after system prompt\r\n\r\n* set seed\r\n\r\n---------\r\n\r\nCo-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>","shortMessageHtmlLink":"llava : fix tokenization to not add bos between image embeddings and …"}},{"before":"32c54116318929c90fd7ae814cf9b5232cd44c36","after":"89e89599fd095172f8d67903b5e227467420f036","ref":"refs/heads/master","pushedAt":"2023-09-12T00:23:57.000Z","pushType":"push","commitsCount":385,"pusher":{"login":"DavidAlphaFox","name":"David.Gao","path":"/DavidAlphaFox","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1024948?s=80&v=4"},"commit":{"message":"CUDA: fix mul_mat_q not used for output tensor (#3127)","shortMessageHtmlLink":"CUDA: fix mul_mat_q not used for output tensor (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1891176977\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/3127\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/3127/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/3127\">ggerganov#3127</a>)"}},{"before":"92549202659fc23ba9fec5e688227d0da9b06b40","after":"32c54116318929c90fd7ae814cf9b5232cd44c36","ref":"refs/heads/master","pushedAt":"2023-07-14T00:23:04.253Z","pushType":"push","commitsCount":161,"pusher":{"login":"DavidAlphaFox","name":"David.Gao","path":"/DavidAlphaFox","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1024948?s=80&v=4"},"commit":{"message":"Revert \"Support using mmap when applying LoRA (#2095)\" (#2206)\n\nHas perf regression when mlock is used.\r\n\r\nThis reverts commit 2347463201a9f4159ae95b737e1544dd300569c8.","shortMessageHtmlLink":"Revert \"Support using mmap when applying LoRA (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1787396429\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/2095\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/2095/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/2095\">ggerganov#2095</a>)\" (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1801916356\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/2206\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/2206/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/2206\">gger…</a>"}},{"before":"92549202659fc23ba9fec5e688227d0da9b06b40","after":"32c54116318929c90fd7ae814cf9b5232cd44c36","ref":"refs/heads/master","pushedAt":"2023-07-14T00:23:04.000Z","pushType":"push","commitsCount":161,"pusher":{"login":"DavidAlphaFox","name":"David.Gao","path":"/DavidAlphaFox","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1024948?s=80&v=4"},"commit":{"message":"Revert \"Support using mmap when applying LoRA (#2095)\" (#2206)\n\nHas perf regression when mlock is used.\r\n\r\nThis reverts commit 2347463201a9f4159ae95b737e1544dd300569c8.","shortMessageHtmlLink":"Revert \"Support using mmap when applying LoRA (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1787396429\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/2095\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/2095/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/2095\">ggerganov#2095</a>)\" (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1801916356\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/2206\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/2206/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/2206\">gger…</a>"}}],"hasNextPage":false,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEWKVx2AA","startCursor":null,"endCursor":null}},"title":"Activity · DavidAlphaFox/llama.cpp"}