{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":654122609,"defaultBranch":"main","name":"lmdeploy","ownerLogin":"InternLM","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2023-06-15T12:38:06.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/135356492?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1719285085.0","currentOid":""},"activityList":{"items":[{"before":"a39d871c973d5393885484f3d723c84a6d77ccc5","after":"2a02bbe62bfc5c0088f7e569ca5352e44cecd142","ref":"refs/heads/bump-version","pushedAt":"2024-06-26T10:12:04.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"update supported models","shortMessageHtmlLink":"update supported models"}},{"before":"378c6d3aa8e194c8f602f8ec9c51ca766a4b1c48","after":"052f5509fb93056177b33c08379a4c8ecd7ae91f","ref":"refs/heads/main","pushedAt":"2024-06-26T08:49:41.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"react test evaluation config (#1861)\n\n* update\r\n\r\n* update\r\n\r\n* update","shortMessageHtmlLink":"react test evaluation config (#1861)"}},{"before":"b672f3ad9ba63cded818b9658e3a864bb0618050","after":"a39d871c973d5393885484f3d723c84a6d77ccc5","ref":"refs/heads/bump-version","pushedAt":"2024-06-26T08:45:26.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"update news","shortMessageHtmlLink":"update news"}},{"before":"eb78bca51c1fe99ade64dd0452e10262dc577987","after":"b672f3ad9ba63cded818b9658e3a864bb0618050","ref":"refs/heads/bump-version","pushedAt":"2024-06-26T08:09:42.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"update news","shortMessageHtmlLink":"update news"}},{"before":"a06174f836882d853d4eb18519c2245c2a7eae8c","after":"378c6d3aa8e194c8f602f8ec9c51ca766a4b1c48","ref":"refs/heads/main","pushedAt":"2024-06-26T06:08:28.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"misc: align PyTorch Engine temprature with TurboMind (#1850)","shortMessageHtmlLink":"misc: align PyTorch Engine temprature with TurboMind (#1850)"}},{"before":"44f5f25bc5bd39e54a0368ff10974e9382fdfab3","after":"eb78bca51c1fe99ade64dd0452e10262dc577987","ref":"refs/heads/bump-version","pushedAt":"2024-06-25T10:23:58.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"bump version to v0.5.0","shortMessageHtmlLink":"bump version to v0.5.0"}},{"before":"c59a70413c3600fb22e683c46e085758272e4178","after":"a06174f836882d853d4eb18519c2245c2a7eae8c","ref":"refs/heads/main","pushedAt":"2024-06-25T09:04:26.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"remove chat template config in turbomind engine (#1161)\n\n* remove .model of turbomind engine\r\n\r\n* update async engine init\r\n\r\n* remove unused\r\n\r\n* remove chat_template_config\r\n\r\n* remove chat_template_config\r\n\r\n* add max_batch_size for lmdeploy.chat cli\r\n\r\n* update batch size\r\n\r\n* fix lint\r\n\r\n* fix chat_template_config.capability\r\n\r\n* remove chat_template & cap in old cli\r\n\r\n* update","shortMessageHtmlLink":"remove chat template config in turbomind engine (#1161)"}},{"before":"a5aeee34142fef6a12fba53c09889d4a293572d0","after":"c59a70413c3600fb22e683c46e085758272e4178","ref":"refs/heads/main","pushedAt":"2024-06-25T04:18:26.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Add interfaces to the pipeline to obtain logits and ppl (#1652)\n\n* pipeline ppl\r\n\r\n* turbomind decode support embeddings input\r\n\r\n* pipeline get_logtis support embeddings input\r\n\r\n* add prepare_inputs\r\n\r\n* update docs\r\n\r\n* fix long session ppl\r\n\r\n* fix lint\r\n\r\n* fix unequal session_len of turbomind and pipeline\r\n\r\n* reduce memory\r\n\r\n* fix pytorch engine crush\r\n\r\n* pytorch engine decode embeddings\r\n\r\n* remove do_preprocess\r\n\r\n* Revert \"fix unequal session_len of turbomind and pipeline\"\r\n\r\nThis reverts commit 0b0508a27003e797e251af63d89f24b116c72f37.\r\n\r\n* fix template\r\n\r\n* fix size\r\n\r\n* fix\r\n\r\n* update docs\r\n\r\n* fix steps\r\n\r\n* remove convert to numpy\r\n\r\n* update docs","shortMessageHtmlLink":"Add interfaces to the pipeline to obtain logits and ppl (#1652)"}},{"before":null,"after":"a5aeee34142fef6a12fba53c09889d4a293572d0","ref":"refs/heads/support-910b","pushedAt":"2024-06-25T03:11:25.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"grimoire","name":"q.yao","path":"/grimoire","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1239736?s=80&v=4"},"commit":{"message":"Support Qwen2-1.5b awq (#1793)\n\n* Support Qwen2-1.5b awq\r\n\r\n* remove","shortMessageHtmlLink":"Support Qwen2-1.5b awq (#1793)"}},{"before":"991c13b049c0d49a5082ca08b787710d5f7baad9","after":"a5aeee34142fef6a12fba53c09889d4a293572d0","ref":"refs/heads/main","pushedAt":"2024-06-24T11:42:21.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Support Qwen2-1.5b awq (#1793)\n\n* Support Qwen2-1.5b awq\r\n\r\n* remove","shortMessageHtmlLink":"Support Qwen2-1.5b awq (#1793)"}},{"before":"fa6f8d2f04fb834a4434e80beac4acc90054ba94","after":"991c13b049c0d49a5082ca08b787710d5f7baad9","ref":"refs/heads/main","pushedAt":"2024-06-24T11:41:09.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Harden stream callback (#1838)\n\n* harden stream callback\r\n\r\n* fix lint","shortMessageHtmlLink":"Harden stream callback (#1838)"}},{"before":"940fda3648d90bc51b69e2ad6236d86bb2866b24","after":"3c7aa88fb9ee05aa6f8b3abb48c3019c6610c353","ref":"refs/heads/dev","pushedAt":"2024-06-24T10:01:02.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"lzhangzz","name":"Li Zhang","path":"/lzhangzz","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/19465119?s=80&v=4"},"commit":{"message":"fix lint","shortMessageHtmlLink":"fix lint"}},{"before":"74f8f4d24ec03410fb4f5f05de149744bbe9b812","after":"fa6f8d2f04fb834a4434e80beac4acc90054ba94","ref":"refs/heads/main","pushedAt":"2024-06-24T09:10:11.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"fix image encoder request queue (#1837)","shortMessageHtmlLink":"fix image encoder request queue (#1837)"}},{"before":"ff37bbf05c2b3ce877e77b650a1a254ff7769ec8","after":"74f8f4d24ec03410fb4f5f05de149744bbe9b812","ref":"refs/heads/main","pushedAt":"2024-06-24T09:02:03.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Support internvl-chat for pytorch engine (#1797)\n\n* support internvl v1.5\r\n\r\n* update engine\r\n\r\n* fix comment\r\n\r\n* fix\r\n\r\n* fix trust_remote_code","shortMessageHtmlLink":"Support internvl-chat for pytorch engine (#1797)"}},{"before":"e3926b65aa1d0f0ce99041290aaa8b2b0f8bfc66","after":"ff37bbf05c2b3ce877e77b650a1a254ff7769ec8","ref":"refs/heads/main","pushedAt":"2024-06-24T08:24:22.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Add model revision & download_dir to cli (#1814)\n\n* add model revision & download_dir to cli\r\n\r\n* update get_model","shortMessageHtmlLink":"Add model revision & download_dir to cli (#1814)"}},{"before":"da439dfd186265faf8074797f5ed4c8a3f3c4f2d","after":"e3926b65aa1d0f0ce99041290aaa8b2b0f8bfc66","ref":"refs/heads/main","pushedAt":"2024-06-24T08:21:43.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"compat internlm2 for pytorch engine (#1825)\n\n* compat\r\n\r\n* fix lite","shortMessageHtmlLink":"compat internlm2 for pytorch engine (#1825)"}},{"before":"7de38e06fa582dea865962e655efc0136e30026e","after":"da439dfd186265faf8074797f5ed4c8a3f3c4f2d","ref":"refs/heads/main","pushedAt":"2024-06-24T03:52:03.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Torch deepseek v2 (#1621)\n\n* first\r\n\r\n* all model down\r\n\r\n* remove device mesh\r\n\r\n* fix triton==2.2.0\r\n\r\n* WIP\r\n\r\n* first\r\n\r\n* load model weights\r\n\r\n* wip\r\n\r\n* done\r\n\r\n* support shared kv\r\n\r\n* pre-alloc output\r\n\r\n* fix ut\r\n\r\n* enlarge num warps\r\n\r\n* add warning\r\n\r\n* update mha kernel\r\n\r\n* dynamic share kv\r\n\r\n* adjust num warps\r\n\r\n* autotuning\r\n\r\n* support lite\r\n\r\n* remove autotune\r\n\r\n* split dmodel\r\n\r\n* inplace rms\r\n\r\n* update support model\r\n\r\n* fix ut\r\n\r\n* update block size automatically","shortMessageHtmlLink":"Torch deepseek v2 (#1621)"}},{"before":"fd0cefbdecfe80bcfb2db3eedf70d55d8f15d19e","after":"7de38e06fa582dea865962e655efc0136e30026e","ref":"refs/heads/main","pushedAt":"2024-06-24T03:07:58.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Update engine.py to fix typo (#1829)\n\nsmall typo","shortMessageHtmlLink":"Update engine.py to fix typo (#1829)"}},{"before":"4067cb241265a7f1d6e2925bbe7adeab63b72721","after":"fd0cefbdecfe80bcfb2db3eedf70d55d8f15d19e","ref":"refs/heads/main","pushedAt":"2024-06-22T10:44:23.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"detokenize with prompt token ids (#1753)","shortMessageHtmlLink":"detokenize with prompt token ids (#1753)"}},{"before":"21533e798c944071b6c16c0666779f1056a7c0a3","after":"4067cb241265a7f1d6e2925bbe7adeab63b72721","ref":"refs/heads/main","pushedAt":"2024-06-21T14:01:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Fix qwen-vl-chat hung (#1824)","shortMessageHtmlLink":"Fix qwen-vl-chat hung (#1824)"}},{"before":"a7a50c5efbfe876a0218f4771042eb29bdcd3c31","after":"21533e798c944071b6c16c0666779f1056a7c0a3","ref":"refs/heads/main","pushedAt":"2024-06-21T13:46:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"AsyncEngine create cancel task in exception. (#1807)\n\n* update task, optimize thread safe\r\n\r\n* optimize request\r\n\r\n* move event loop\r\n\r\n* add TODO","shortMessageHtmlLink":"AsyncEngine create cancel task in exception. (#1807)"}},{"before":"e95213dad233463f278e89eeffa07b93ce6dcff0","after":"a7a50c5efbfe876a0218f4771042eb29bdcd3c31","ref":"refs/heads/main","pushedAt":"2024-06-21T12:39:54.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Fix Request completed log (#1821)","shortMessageHtmlLink":"Fix Request completed log (#1821)"}},{"before":"78912ca62734cf29bcbbdf24e3aa3dfcdc398c82","after":"e95213dad233463f278e89eeffa07b93ce6dcff0","ref":"refs/heads/main","pushedAt":"2024-06-21T11:15:21.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Add GLM-4-9B-Chat (#1724)\n\n* add glm-4-9b-chat\r\n\r\n* fix typo\r\n\r\n* update supported models\r\n\r\n* fix lint\r\n\r\n* chatglm2/3 compatibility\r\n\r\n* fix lint\r\n\r\n* fix typo\r\n\r\n* fix\r\n\r\n* add derived class ChatGLM4Tokenizer\r\n\r\n* update\r\n\r\n* add ut for ChatGLM4Tokenizer\r\n\r\n* update glm4 chat template and add its ut\r\n\r\n* update\r\n\r\n* fix\r\n\r\n* rotary_embedding_dim\r\n\r\n* fix\r\n\r\n---------\r\n\r\nCo-authored-by: lvhan028 ","shortMessageHtmlLink":"Add GLM-4-9B-Chat (#1724)"}},{"before":"3b39322dd939c7f12b16d096ac62d13cecfbd0e7","after":"78912ca62734cf29bcbbdf24e3aa3dfcdc398c82","ref":"refs/heads/main","pushedAt":"2024-06-21T09:23:25.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"PyTorchEngine support the latest internlm2 modeling. (#1798)\n\n* update rewrite of internlm2\r\n\r\n* fix w8a8","shortMessageHtmlLink":"PyTorchEngine support the latest internlm2 modeling. (#1798)"}},{"before":"9e8cb3c4948c0160f00d5401d4519b192aee6581","after":"3b39322dd939c7f12b16d096ac62d13cecfbd0e7","ref":"refs/heads/main","pushedAt":"2024-06-21T08:49:47.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Device dispatcher (#1775)\n\n* support triton 2.3.0\r\n\r\n* fix triton2.1\r\n\r\n* interpret mode\r\n\r\n* add 230 wrapper\r\n\r\n* add wrapper for triton==2.2.0\r\n\r\n* add hint\r\n\r\n* add num_warps and num_stages\r\n\r\n* fix autotune\r\n\r\n* custom type hint\r\n\r\n* support triton231\r\n\r\n* cache cuda options\r\n\r\n* update typehint\r\n\r\n* fix for python<3.10\r\n\r\n* switch device\r\n\r\n* remove api\r\n\r\n* context update\r\n\r\n* default device","shortMessageHtmlLink":"Device dispatcher (#1775)"}},{"before":"07e0c79fcd55a5e421a378a42111cb9b315cc6c0","after":"9e8cb3c4948c0160f00d5401d4519b192aee6581","ref":"refs/heads/main","pushedAt":"2024-06-20T20:40:51.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"fix best_match_model (#1812)\n\n* fix best_match_model\r\n\r\n* fix\r\n\r\n* update test","shortMessageHtmlLink":"fix best_match_model (#1812)"}},{"before":"4eaf4738c0342c30657fa77a4eeebd7f6bf82b4c","after":"07e0c79fcd55a5e421a378a42111cb9b315cc6c0","ref":"refs/heads/main","pushedAt":"2024-06-20T12:51:22.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"check driver mismatch (#1811)\n\n* check driver mismatch\r\n\r\n* update","shortMessageHtmlLink":"check driver mismatch (#1811)"}},{"before":"90c3773aa81ebd339f6fc529695e2579eb38cbbe","after":"4eaf4738c0342c30657fa77a4eeebd7f6bf82b4c","ref":"refs/heads/main","pushedAt":"2024-06-20T08:20:59.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"fix pr test for newest internlm2 model (#1806)\n\n* update\r\n\r\n* update\r\n\r\n* update\r\n\r\n* update\r\n\r\n* update\r\n\r\n* update","shortMessageHtmlLink":"fix pr test for newest internlm2 model (#1806)"}},{"before":"e73eb55c0ed3b6a77a414718fcd9a9d4056324ba","after":"90c3773aa81ebd339f6fc529695e2579eb38cbbe","ref":"refs/heads/main","pushedAt":"2024-06-19T08:23:40.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"feat: auto set awq model_format from hf (#1799)\n\n* auto set awq model_format from hf\r\n\r\n* fix comment","shortMessageHtmlLink":"feat: auto set awq model_format from hf (#1799)"}},{"before":"dac8b2a030392e7d8cbdf4e5fbf5837d9c94c459","after":"e73eb55c0ed3b6a77a414718fcd9a9d4056324ba","ref":"refs/heads/main","pushedAt":"2024-06-19T06:38:40.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"lvhan028","name":"Lyu Han","path":"/lvhan028","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/4560679?s=80&v=4"},"commit":{"message":"Optimize kernel launch for triton2.2.0 and triton2.3.0 (#1499)\n\n* support triton 2.3.0\r\n\r\n* fix triton2.1\r\n\r\n* interpret mode\r\n\r\n* add 230 wrapper\r\n\r\n* add wrapper for triton==2.2.0\r\n\r\n* add hint\r\n\r\n* add num_warps and num_stages\r\n\r\n* fix autotune\r\n\r\n* custom type hint\r\n\r\n* support triton231\r\n\r\n* cache cuda options\r\n\r\n* update typehint\r\n\r\n* fix for python<3.10\r\n\r\n* remove u64","shortMessageHtmlLink":"Optimize kernel launch for triton2.2.0 and triton2.3.0 (#1499)"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEb5KhgAA","startCursor":null,"endCursor":null}},"title":"Activity ยท InternLM/lmdeploy"}