{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":653567769,"defaultBranch":"main","name":"xFasterTransformer","ownerLogin":"intel","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2023-06-14T09:52:28.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/17888862?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1722413292.0","currentOid":""},"activityList":{"items":[{"before":"59a9430d4ee2ca99de4ca4ea78b9f3eba868e900","after":"cad05924e5d0868aa2a38ad5aea06babb81a6f02","ref":"refs/heads/main","pushedAt":"2024-09-18T02:23:39.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Demo] Web demo with openai-compatible api. (#40)","shortMessageHtmlLink":"[Demo] Web demo with openai-compatible api. (#40)"}},{"before":"d1d03f2a97aedcc2e399c592770987cdb2cc0a17","after":"59a9430d4ee2ca99de4ca4ea78b9f3eba868e900","ref":"refs/heads/main","pushedAt":"2024-09-02T08:51:17.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[quantization] update xFT quantization (#33)","shortMessageHtmlLink":"[quantization] update xFT quantization (#33)"}},{"before":"87867f2dee3935559a16372c81c1a1c0035b86f3","after":"d1d03f2a97aedcc2e399c592770987cdb2cc0a17","ref":"refs/heads/main","pushedAt":"2024-08-21T07:44:10.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Tools] Fix os access control risk. (#37)","shortMessageHtmlLink":"[Tools] Fix os access control risk. (#37)"}},{"before":"420a493f5c3c74f5fdd786f5399aacd04e021df7","after":"87867f2dee3935559a16372c81c1a1c0035b86f3","ref":"refs/heads/main","pushedAt":"2024-08-21T04:39:13.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Comm] Merge `dlopen` call into a inline func. (#35)","shortMessageHtmlLink":"[Comm] Merge dlopen call into a inline func. (#35)"}},{"before":"dd442915ec134f1d103ed2469dcaceda9c430fa0","after":"420a493f5c3c74f5fdd786f5399aacd04e021df7","ref":"refs/heads/main","pushedAt":"2024-08-09T02:59:20.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[API] add transA and transB function for invokeGemm (#32)","shortMessageHtmlLink":"[API] add transA and transB function for invokeGemm (#32)"}},{"before":"df57cb20f5ce90c86e9e8de4cdfd54fb4d027046","after":"dd442915ec134f1d103ed2469dcaceda9c430fa0","ref":"refs/heads/main","pushedAt":"2024-08-02T05:22:12.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[API] Add invoke gemm (#31)\n\nSigned-off-by: Wenhuan Huang ","shortMessageHtmlLink":"[API] Add invoke gemm (#31)"}},{"before":"c1bbfc2775008519e4e408a2275ca91eaa5981a7","after":"df57cb20f5ce90c86e9e8de4cdfd54fb4d027046","ref":"refs/heads/main","pushedAt":"2024-07-31T08:04:18.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Version] v1.8.1. (#30)","shortMessageHtmlLink":"[Version] v1.8.1. (#30)"}},{"before":"faa25f4534f72cfce9a5a69c2ac8957657eeaa5e","after":"c1bbfc2775008519e4e408a2275ca91eaa5981a7","ref":"refs/heads/main","pushedAt":"2024-07-26T02:57:28.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Util] Optimize function of create_key (#26)","shortMessageHtmlLink":"[Util] Optimize function of create_key (#26)"}},{"before":"275b673180039618ffc6b4ec15bdf5ace7cbced3","after":"faa25f4534f72cfce9a5a69c2ac8957657eeaa5e","ref":"refs/heads/main","pushedAt":"2024-07-23T01:22:45.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Version] v1.8.0. (#22)","shortMessageHtmlLink":"[Version] v1.8.0. (#22)"}},{"before":"4bea96b2a7c50bee974f143f47f08d6d4c97f760","after":"275b673180039618ffc6b4ec15bdf5ace7cbced3","ref":"refs/heads/main","pushedAt":"2024-07-22T05:12:04.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Kernel] Fix oneDNN primitive memory leak. (#20)","shortMessageHtmlLink":"[Kernel] Fix oneDNN primitive memory leak. (#20)"}},{"before":"16cd8d861ab3dcb77ebc12d40042148c490f6d47","after":"4bea96b2a7c50bee974f143f47f08d6d4c97f760","ref":"refs/heads/main","pushedAt":"2024-07-19T05:14:35.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"Remove unnecessary computing in Attention (#19)","shortMessageHtmlLink":"Remove unnecessary computing in Attention (#19)"}},{"before":"3df0239775e3617211817bb8cba1ac55d71d2794","after":"16cd8d861ab3dcb77ebc12d40042148c490f6d47","ref":"refs/heads/main","pushedAt":"2024-07-18T05:18:30.000Z","pushType":"push","commitsCount":5,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Layers] Fixed heads Split error for distributed GQA (#16)","shortMessageHtmlLink":"[Layers] Fixed heads Split error for distributed GQA (#16)"}},{"before":"fcea26f06e9ebee4e41c8101917ece34ea3af5c8","after":"3df0239775e3617211817bb8cba1ac55d71d2794","ref":"refs/heads/main","pushedAt":"2024-07-10T07:38:45.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"pujiang2018","name":null,"path":"/pujiang2018","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/43156995?s=80&v=4"},"commit":{"message":"Fixed punctuation error in README (#444)","shortMessageHtmlLink":"Fixed punctuation error in README (#444)"}},{"before":"69b91cf328fd2943e9f18ed086e776995f8eee7a","after":"fcea26f06e9ebee4e41c8101917ece34ea3af5c8","ref":"refs/heads/main","pushedAt":"2024-07-09T02:15:35.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"abenmao","name":"Meng,Chen","path":"/abenmao","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/29789552?s=80&v=4"},"commit":{"message":"[Kernel] Upgrade xDNN to v1.5.2 and make AMX_FP16 work (#468)\n\n* Revert \"fix bug of incorrect input offset in CB\"\r\n\r\nThis reverts commit 314e67f1ca09f0e15a4a4d53720a11f878383efe.\r\n\r\n* Make Slim Attention prepared for AMX_FP16; more balanced split in crossAttnByHead\r\n\r\n* upgrade xdnn and make AMX_FP16 work","shortMessageHtmlLink":"[Kernel] Upgrade xDNN to v1.5.2 and make AMX_FP16 work (#468)"}},{"before":"d20d222bfecea4791828d7844d79fdf2531e62eb","after":"5bdb3a68a54540701e9c3edd7e7653471001a009","ref":"refs/heads/pujiang/feature/amx_fp16","pushedAt":"2024-07-08T14:16:51.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"pujiang2018","name":null,"path":"/pujiang2018","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/43156995?s=80&v=4"},"commit":{"message":"upgrade xdnn and make AMX_FP16 work","shortMessageHtmlLink":"upgrade xdnn and make AMX_FP16 work"}},{"before":"bf57d0be73519afabc623a69b22c7f22798bc067","after":"69b91cf328fd2943e9f18ed086e776995f8eee7a","ref":"refs/heads/main","pushedAt":"2024-07-08T01:54:27.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"pujiang2018","name":null,"path":"/pujiang2018","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/43156995?s=80&v=4"},"commit":{"message":"[Kernel] Make SelfAttention prepared for AMX_FP16; More balanced task split in Cross Attention (#466)","shortMessageHtmlLink":"[Kernel] Make SelfAttention prepared for AMX_FP16; More balanced task…"}},{"before":null,"after":"d20d222bfecea4791828d7844d79fdf2531e62eb","ref":"refs/heads/pujiang/feature/amx_fp16","pushedAt":"2024-07-05T03:47:44.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"pujiang2018","name":null,"path":"/pujiang2018","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/43156995?s=80&v=4"},"commit":{"message":"Make Slim Attention prepared for AMX_FP16; more balanced split in crossAttnByHead","shortMessageHtmlLink":"Make Slim Attention prepared for AMX_FP16; more balanced split in cro…"}},{"before":"37e7ab1e01faf7a4701c2220c76014ff7392772f","after":null,"ref":"refs/heads/pujiang/feature/cb_dev","pushedAt":"2024-07-05T03:40:19.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"pujiang2018","name":null,"path":"/pujiang2018","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/43156995?s=80&v=4"}},{"before":"399ce889c35013afcc439df01b38b8f6bad8cada","after":null,"ref":"refs/heads/pujiang/feature/cont_batch","pushedAt":"2024-07-05T03:39:51.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"pujiang2018","name":null,"path":"/pujiang2018","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/43156995?s=80&v=4"}},{"before":"98c9d32017f15c775f84462d671eed9899040690","after":"bf57d0be73519afabc623a69b22c7f22798bc067","ref":"refs/heads/main","pushedAt":"2024-07-04T06:11:05.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Readme] Add accepted papers (#465)","shortMessageHtmlLink":"[Readme] Add accepted papers (#465)"}},{"before":"3551150a6340c23a9495acdbad50ee9cba10ae48","after":"98c9d32017f15c775f84462d671eed9899040690","ref":"refs/heads/main","pushedAt":"2024-07-04T05:27:36.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Layers] Fix invokeAttentionLLaMA API (#464)","shortMessageHtmlLink":"[Layers] Fix invokeAttentionLLaMA API (#464)"}},{"before":"ab08fe524357ecaa29659fa895b3ee2ca8dc162b","after":"3551150a6340c23a9495acdbad50ee9cba10ae48","ref":"refs/heads/main","pushedAt":"2024-07-02T08:55:28.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"abenmao","name":"Meng,Chen","path":"/abenmao","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/29789552?s=80&v=4"},"commit":{"message":"[Layers] Enable AMX FP16 of FlashAttn (#459)","shortMessageHtmlLink":"[Layers] Enable AMX FP16 of FlashAttn (#459)"}},{"before":"6656c547bf32b6a000c780fdb49991aedda203b4","after":"ab08fe524357ecaa29659fa895b3ee2ca8dc162b","ref":"refs/heads/main","pushedAt":"2024-07-02T02:35:11.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Dependency] Bump web_demo requirement. (#463)","shortMessageHtmlLink":"[Dependency] Bump web_demo requirement. (#463)"}},{"before":null,"after":"d01f0fda291ef664ed27b19d533d8ed302cfc36f","ref":"refs/heads/v1.7.3-rls","pushedAt":"2024-06-27T01:01:42.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Version] v1.7.3.","shortMessageHtmlLink":"[Version] v1.7.3."}},{"before":"c81d7f2b7d8b2f556054db341c080af93095c3ba","after":"6656c547bf32b6a000c780fdb49991aedda203b4","ref":"refs/heads/main","pushedAt":"2024-06-27T00:54:59.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Denpendency] Pin python requirements.txt version. (#458)","shortMessageHtmlLink":"[Denpendency] Pin python requirements.txt version. (#458)"}},{"before":"0ce383bd7873fe6b2da5ea6bbfda38e5904bb0e1","after":"c81d7f2b7d8b2f556054db341c080af93095c3ba","ref":"refs/heads/main","pushedAt":"2024-06-27T00:54:35.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Duyi-Wang","name":null,"path":"/Duyi-Wang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/83744562?s=80&v=4"},"commit":{"message":"[Kernel] Cache oneDNN primitive when M < `XFT_PRIMITIVE_CACHE_M`, default 256. (#460)","shortMessageHtmlLink":"[Kernel] Cache oneDNN primitive when M < XFT_PRIMITIVE_CACHE_M, def…"}},{"before":"956fae6ae12a1803374d36f5916138a33b0dc76a","after":"0ce383bd7873fe6b2da5ea6bbfda38e5904bb0e1","ref":"refs/heads/main","pushedAt":"2024-06-25T03:19:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"changqi1","name":"Changqing Li","path":"/changqi1","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/33472713?s=80&v=4"},"commit":{"message":"[Kernel] Enable AMX FP16 on GNR. (#456)\n\nneed export env DNNL_MAX_CPU_ISA=AVX512_CORE_AMX_FP16 when compiling and running\r\n\r\nSigned-off-by: Wenhuan Huang ","shortMessageHtmlLink":"[Kernel] Enable AMX FP16 on GNR. (#456)"}},{"before":"df789baca7927f5cf06df1b8df98c411d30d7822","after":"956fae6ae12a1803374d36f5916138a33b0dc76a","ref":"refs/heads/main","pushedAt":"2024-06-19T07:38:19.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"abenmao","name":"Meng,Chen","path":"/abenmao","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/29789552?s=80&v=4"},"commit":{"message":"[Bugfix] fixed shm reduceAdd & rope error when batch size is large (#457)","shortMessageHtmlLink":"[Bugfix] fixed shm reduceAdd & rope error when batch size is large (#457"}},{"before":"da2a7faaf215673e2c86677dfeb932bc38bf61d6","after":"df789baca7927f5cf06df1b8df98c411d30d7822","ref":"refs/heads/main","pushedAt":"2024-06-18T09:26:40.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"changqi1","name":"Changqing Li","path":"/changqi1","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/33472713?s=80&v=4"},"commit":{"message":"[Kernel] Enable continuous batching on single GPU. (#452)","shortMessageHtmlLink":"[Kernel] Enable continuous batching on single GPU. (#452)"}},{"before":"cc9675f9d9c70b39702fdbaa71820591165355da","after":"da2a7faaf215673e2c86677dfeb932bc38bf61d6","ref":"refs/heads/main","pushedAt":"2024-06-18T03:29:13.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"a3213105","name":"sheng.gui@intel.com","path":"/a3213105","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/12908251?s=80&v=4"},"commit":{"message":"[Version] v1.7.2. (#454)","shortMessageHtmlLink":"[Version] v1.7.2. (#454)"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"startCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wOS0xOFQwMjoyMzozOS4wMDAwMDBazwAAAAS5KPVW","endCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wNi0xOFQwMzoyOToxMy4wMDAwMDBazwAAAARoAD2O"}},"title":"Activity · intel/xFasterTransformer"}