{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":178075572,"defaultBranch":"master","name":"kserve","ownerLogin":"kserve","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2019-03-27T21:14:14.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/83512434?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1716285450.0","currentOid":""},"activityList":{"items":[{"before":"edac2c3c8bc1c4d8fa0e87061abf749e4a0d397c","after":"1c51eeee174330b076e4171e6d71e9138f2510b3","ref":"refs/heads/master","pushedAt":"2024-06-03T13:50:11.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Update serving runtimes package version 0.13.0 (#3720)\n\nupdate version to 0.13.0\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan ","shortMessageHtmlLink":"Update serving runtimes package version 0.13.0 (#3720)"}},{"before":"ff744c60f3189224e5724b7b2fdd6ebf567db327","after":"edac2c3c8bc1c4d8fa0e87061abf749e4a0d397c","ref":"refs/heads/master","pushedAt":"2024-06-03T13:43:36.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fix prompt token count and provide completion usage in OpenAI response (#3712)\n\n* Fix input token count and add completion usage\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Add max_length for test models\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n---------\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan ","shortMessageHtmlLink":"Fix prompt token count and provide completion usage in OpenAI response ("}},{"before":"16c90170721e6c2ed121204fa848d41e9f4f4e96","after":"ff744c60f3189224e5724b7b2fdd6ebf567db327","ref":"refs/heads/master","pushedAt":"2024-06-03T10:25:59.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fixup max_length for HF and model info for vLLM (#3715)\n\n* Fixup max_length for HF and model info for vLLM\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Use vLLM's implementation for max_length\r\n\r\nAlso fixup error in calculating input sequence lenngth\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Fixup linter\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Add license to new file\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Add bloom test case for max_tokens\r\n\r\nRevert input length fix\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Set limit on opt chat competion e2e test\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n---------\r\n\r\nSigned-off-by: Dattu Sharma ","shortMessageHtmlLink":"Fixup max_length for HF and model info for vLLM (#3715)"}},{"before":"71114b62b5981df0dbedef09d49c867013eebb20","after":"16c90170721e6c2ed121204fa848d41e9f4f4e96","ref":"refs/heads/master","pushedAt":"2024-06-03T00:18:35.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Publish 0.13 release (#3719)\n\nSigned-off-by: Dan Sun ","shortMessageHtmlLink":"Publish 0.13 release (#3719)"}},{"before":"4b58775f640de61125e00ef81482d8ace665191a","after":"71114b62b5981df0dbedef09d49c867013eebb20","ref":"refs/heads/master","pushedAt":"2024-06-02T23:50:36.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fix model_id and model_dir precedence for vLLM (#3718)\n\nFix model_id and model_dir precendence\r\n\r\nSigned-off-by: Dan Sun ","shortMessageHtmlLink":"Fix model_id and model_dir precedence for vLLM (#3718)"}},{"before":"d3934869c79de8ce8fd9ec872c4b0dbd16624f16","after":"4b58775f640de61125e00ef81482d8ace665191a","ref":"refs/heads/master","pushedAt":"2024-06-02T21:23:11.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Typos and minor fixes (#3429)\n\nSigned-off-by: Alex Peters \r\nSigned-off-by: Dan Sun \r\nCo-authored-by: Dan Sun ","shortMessageHtmlLink":"Typos and minor fixes (#3429)"}},{"before":"c660972ea153a197a483efb23b5c5e036eb4504c","after":"d3934869c79de8ce8fd9ec872c4b0dbd16624f16","ref":"refs/heads/master","pushedAt":"2024-06-02T20:37:26.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Add option for returning probabilities in huggingface server (#3607)\n\n* added flag to return raw prediction results\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* black fix\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* unit test bug fix\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* unittest for token classification\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* verify codegen\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* bug fix\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n---------\r\n\r\nSigned-off-by: Andrews Arokiam ","shortMessageHtmlLink":"Add option for returning probabilities in huggingface server (#3607)"}},{"before":"04c41c21ddafe04be091179c0f9811a10ceac475","after":"c660972ea153a197a483efb23b5c5e036eb4504c","ref":"refs/heads/master","pushedAt":"2024-05-28T04:10:55.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Add FP16 datatype support for OIP grpc (#3695)\n\n* Add FP16 datatype support for OIP grpc\r\nAdd grpc server tests\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Add grpcio-testing as test dependency\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Fix model repository initialization default value\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Remove fp16 global map\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Resolve comments\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n---------\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan ","shortMessageHtmlLink":"Add FP16 datatype support for OIP grpc (#3695)"}},{"before":"c9b3738ade756ea36f2b1fc1f1bcbd2d071ceab4","after":"04c41c21ddafe04be091179c0f9811a10ceac475","ref":"refs/heads/master","pushedAt":"2024-05-27T19:12:00.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Add precaution again running v1 endpoints on openai models (#3694)\n\n* Add precaution again running v1 endpoints on openai models\r\n\r\nSigned-off-by: grandbora \r\n\r\n* Remove the check from explain\r\n\r\nSigned-off-by: grandbora \r\n\r\n* Add a warning log for explain\r\n\r\nSigned-off-by: grandbora \r\n\r\n---------\r\n\r\nSigned-off-by: grandbora ","shortMessageHtmlLink":"Add precaution again running v1 endpoints on openai models (#3694)"}},{"before":"4841328f51df6b4a18cd451355d5ccf7d9dd72d0","after":"c9b3738ade756ea36f2b1fc1f1bcbd2d071ceab4","ref":"refs/heads/master","pushedAt":"2024-05-27T08:38:19.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Copy generated CRDs by kustomize to Helm (#3392)\n\nfix conflict\r\n\r\nSigned-off-by: jooho ","shortMessageHtmlLink":"Copy generated CRDs by kustomize to Helm (#3392)"}},{"before":"690e269ac1aa88d6e15872164c966305cd518169","after":"4841328f51df6b4a18cd451355d5ccf7d9dd72d0","ref":"refs/heads/master","pushedAt":"2024-05-22T11:32:37.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fix kserve version is not updated properly by python-release.sh (#3707)\n\nSigned-off-by: Sivanantham Chinnaiyan ","shortMessageHtmlLink":"Fix kserve version is not updated properly by python-release.sh (#3707)"}},{"before":"247008c9323b669f69c84d50419d7c184110bebe","after":"6c37dce17c652ebc82ad956f04a5c2badb04c8a4","ref":"refs/heads/release-0.13","pushedAt":"2024-05-21T09:56:22.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Release v0.13.0-rc1 (#3704)\n\n* Release v0.13.0-rc1\n\nSigned-off-by: Johnu George ","shortMessageHtmlLink":"Release v0.13.0-rc1 (#3704)"}},{"before":"16d391be4b211b3afb624016d6da1a6da433909a","after":"247008c9323b669f69c84d50419d7c184110bebe","ref":"refs/heads/release-0.13","pushedAt":"2024-05-21T09:53:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Release v0.13.0-rc1 (#3704)\n\n* Release v0.13.0-rc1\r\n\r\nSigned-off-by: Johnu George ","shortMessageHtmlLink":"Release v0.13.0-rc1 (#3704)"}},{"before":"1fa44e9f3bb40014e70b556331b449c52f3ccf3c","after":"690e269ac1aa88d6e15872164c966305cd518169","ref":"refs/heads/master","pushedAt":"2024-05-21T09:05:07.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Add the field ResponseStartTimeoutSeconds to create ksvc (#3705)\n\nSigned-off-by: Vincent Hou ","shortMessageHtmlLink":"Add the field ResponseStartTimeoutSeconds to create ksvc (#3705)"}},{"before":"6f155a188ab90ea7f2b78b394a9beb7a150f0ea2","after":"1fa44e9f3bb40014e70b556331b449c52f3ccf3c","ref":"refs/heads/master","pushedAt":"2024-05-20T13:33:37.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Remove conversion webhook from kubeflow manifest patch (#3700)\n\nRemove conversion webhook from kubeflow\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan ","shortMessageHtmlLink":"Remove conversion webhook from kubeflow manifest patch (#3700)"}},{"before":"8771c3d7be1ae22835b2d10491ae80ff35ef6841","after":"6f155a188ab90ea7f2b78b394a9beb7a150f0ea2","ref":"refs/heads/master","pushedAt":"2024-05-19T16:25:29.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Unify the log configuration using kserve logger (#3577)\n\n* Configure logging for serving runtimes\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Add pyyaml dependency\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* black format\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* fix pyproject.toml\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Rebase master\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* cleanup logger for e2e\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Modify logger format to include func name\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Log model download time.\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Rebase master\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Allow disabling logger configuration and deprecate logger related arg in model server\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Rebase master\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Resolve comments\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* pyyaml=^6.0.0 to fix build failure\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n* Remove logger related parameters from model server\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan \r\n\r\n---------\r\n\r\nSigned-off-by: Sivanantham Chinnaiyan ","shortMessageHtmlLink":"Unify the log configuration using kserve logger (#3577)"}},{"before":"bfc2e21f50cbfd32c979afee2841ffe25000c7f4","after":"16d391be4b211b3afb624016d6da1a6da433909a","ref":"refs/heads/release-0.13","pushedAt":"2024-05-18T23:29:27.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"oss-prow-bot[bot]","name":null,"path":"/apps/oss-prow-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/658040?s=80&v=4"},"commit":{"message":" Merge changes from master to release-0.13 branch (#3698)\n\n* upgrade vllm/transformers version (#3671)\n\nupgrade vllm version\r\n\r\nSigned-off-by: Johnu George \n\n* Add openai models endpoint (#3666)\n\nSigned-off-by: Curtis Maddalozzo \n\n* feat: Support customizable deployment strategy for RawDeployment mode. Fixes #3452 (#3603)\n\n* feat: Support customizable deployment strategy for RawDeployment mode\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* regen\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* lint\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Correctly apply rollingupdate\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* address comments\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Add validation\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n---------\r\n\r\nSigned-off-by: Yuan Tang \n\n* Enable dtype support for huggingface server (#3613)\n\n* Enable dtype for huggingface server\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Set float16 as default. Fixup linter\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Add small comment to make the changes understandable\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Fixup linter\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Adapt to new huggingfacemodel\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Fixup merge :)\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Explicitly mention the behaviour of dtype flag on auto.\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Default to FP32 for encoder models\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Selectively add --dtype to parser. Use FP16 for GPU and FP32 for CPU\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Fixup linter\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Update poetry\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Use torch.float32 forr tests explicitly\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n---------\r\n\r\nSigned-off-by: Dattu Sharma \n\n* Add method for checking model health/readiness (#3673)\n\nSigned-off-by: Curtis Maddalozzo \n\n* fix for extract zip from gcs (#3510)\n\n* fix for extract zip from gcs\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* initial commit for gcs model download unittests\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* unittests for model download from gcs\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* black format fix\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* code verification\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n---------\r\n\r\nSigned-off-by: Andrews Arokiam \n\n* Update Dockerfile and Readme (#3676)\n\nSigned-off-by: Gavrish Prabhu \n\n* Update huggingface readme (#3678)\n\n* update wording for huggingface README\r\n\r\nsmall update to make readme easier to understand\r\n\r\nSigned-off-by: Alexa Griffith \r\n\r\n* Update README.md\r\n\r\nSigned-off-by: Alexa Griffith agriffith50@bloomberg.net\r\n\r\n* Update python/huggingfaceserver/README.md\r\n\r\nCo-authored-by: Filippe Spolti \r\nSigned-off-by: Alexa Griffith \r\n\r\n* update vllm\r\n\r\nSigned-off-by: alexagriffith \r\n\r\n* Update README.md\r\n\r\n---------\r\n\r\nSigned-off-by: Alexa Griffith \r\nSigned-off-by: Alexa Griffith agriffith50@bloomberg.net\r\nSigned-off-by: alexagriffith \r\nSigned-off-by: Dan Sun \r\nCo-authored-by: Filippe Spolti \r\nCo-authored-by: Dan Sun \n\n* fix: HPA equality check should include annotations (#3650)\n\n* fix: HPA equality check should include annotations\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Only watch related autoscalerclass annotation\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* simplify\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Add missing delete action\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* fix logic\r\n\r\nSigned-off-by: Yuan Tang \r\n---------\r\n\r\nSigned-off-by: Yuan Tang \n\n* Fix: huggingface runtime in helm chart (#3679)\n\nfix huggingface runtime in chart\r\n\r\nSigned-off-by: Dan Sun \n\n* Fix: model id and model dir check order (#3680)\n\n* fix huggingface runtime in chart\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n* Allow model_dir to be specified on template\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n* Default model_dir to /mnt/models for HF\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n* Lint format\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n---------\r\n\r\nSigned-off-by: Dan Sun \n\n* Fix:vLLM Model Supported check throwing circular dependency (#3688)\n\n* Fix:vLLM Model Supported check throwing circular dependency\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* remove unwanted comments\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* remove unwanted comments\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* fix return case\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* fix to check all arch in model config forr vllm support\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* fixlint\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n---------\r\n\r\nSigned-off-by: Gavrish Prabhu \n\n* Fix: Allow null in Finish reason streaming response in vLLM (#3684)\n\nFix: allow null in Finish reason\r\n\r\nSigned-off-by: Gavrish Prabhu \n\n---------\n\nSigned-off-by: Johnu George \nSigned-off-by: Curtis Maddalozzo \nSigned-off-by: Yuan Tang \nSigned-off-by: Dattu Sharma \nSigned-off-by: Andrews Arokiam \nSigned-off-by: Gavrish Prabhu \nSigned-off-by: Alexa Griffith \nSigned-off-by: Alexa Griffith agriffith50@bloomberg.net\nSigned-off-by: alexagriffith \nSigned-off-by: Dan Sun \nCo-authored-by: Curtis Maddalozzo \nCo-authored-by: Yuan Tang \nCo-authored-by: Datta Nimmaturi <39181234+Datta0@users.noreply.github.com>\nCo-authored-by: Andrews Arokiam <87992092+andyi2it@users.noreply.github.com>\nCo-authored-by: Gavrish Prabhu \nCo-authored-by: Alexa Griffith \nCo-authored-by: Filippe Spolti \nCo-authored-by: Dan Sun ","shortMessageHtmlLink":" Merge changes from master to release-0.13 branch (#3698)"}},{"before":"892e5dc6e094058c550985dfc6c6e7bbd470968c","after":"8771c3d7be1ae22835b2d10491ae80ff35ef6841","ref":"refs/heads/master","pushedAt":"2024-05-15T04:11:14.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fix: Allow null in Finish reason streaming response in vLLM (#3684)\n\nFix: allow null in Finish reason\r\n\r\nSigned-off-by: Gavrish Prabhu ","shortMessageHtmlLink":"Fix: Allow null in Finish reason streaming response in vLLM (#3684)"}},{"before":"4c6ce450b6d937862aba6597e673ca6622b45194","after":"892e5dc6e094058c550985dfc6c6e7bbd470968c","ref":"refs/heads/master","pushedAt":"2024-05-15T04:06:46.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fix:vLLM Model Supported check throwing circular dependency (#3688)\n\n* Fix:vLLM Model Supported check throwing circular dependency\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* remove unwanted comments\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* remove unwanted comments\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* fix return case\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* fix to check all arch in model config forr vllm support\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n* fixlint\r\n\r\nSigned-off-by: Gavrish Prabhu \r\n\r\n---------\r\n\r\nSigned-off-by: Gavrish Prabhu ","shortMessageHtmlLink":"Fix:vLLM Model Supported check throwing circular dependency (#3688)"}},{"before":"024f69b963faafa3da6e90ed19da04a11480e01a","after":"4c6ce450b6d937862aba6597e673ca6622b45194","ref":"refs/heads/master","pushedAt":"2024-05-14T12:22:44.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fix: model id and model dir check order (#3680)\n\n* fix huggingface runtime in chart\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n* Allow model_dir to be specified on template\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n* Default model_dir to /mnt/models for HF\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n* Lint format\r\n\r\nSigned-off-by: Dan Sun \r\n\r\n---------\r\n\r\nSigned-off-by: Dan Sun ","shortMessageHtmlLink":"Fix: model id and model dir check order (#3680)"}},{"before":"56a2940358ca14bf65e37b2c7a16bf5a85f73513","after":"024f69b963faafa3da6e90ed19da04a11480e01a","ref":"refs/heads/master","pushedAt":"2024-05-13T09:03:39.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Fix: huggingface runtime in helm chart (#3679)\n\nfix huggingface runtime in chart\r\n\r\nSigned-off-by: Dan Sun ","shortMessageHtmlLink":"Fix: huggingface runtime in helm chart (#3679)"}},{"before":"9dbce8e9653896def6bf3140aa3c08a8c8b3389d","after":"56a2940358ca14bf65e37b2c7a16bf5a85f73513","ref":"refs/heads/master","pushedAt":"2024-05-11T14:00:27.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"fix: HPA equality check should include annotations (#3650)\n\n* fix: HPA equality check should include annotations\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Only watch related autoscalerclass annotation\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* simplify\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Add missing delete action\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* fix logic\r\n\r\nSigned-off-by: Yuan Tang \r\n---------\r\n\r\nSigned-off-by: Yuan Tang ","shortMessageHtmlLink":"fix: HPA equality check should include annotations (#3650)"}},{"before":"a4cce1a96fa0c7d3ecc916bd12505b529ed96337","after":"9dbce8e9653896def6bf3140aa3c08a8c8b3389d","ref":"refs/heads/master","pushedAt":"2024-05-11T13:09:31.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Update huggingface readme (#3678)\n\n* update wording for huggingface README\r\n\r\nsmall update to make readme easier to understand\r\n\r\nSigned-off-by: Alexa Griffith \r\n\r\n* Update README.md\r\n\r\nSigned-off-by: Alexa Griffith agriffith50@bloomberg.net\r\n\r\n* Update python/huggingfaceserver/README.md\r\n\r\nCo-authored-by: Filippe Spolti \r\nSigned-off-by: Alexa Griffith \r\n\r\n* update vllm\r\n\r\nSigned-off-by: alexagriffith \r\n\r\n* Update README.md\r\n\r\n---------\r\n\r\nSigned-off-by: Alexa Griffith \r\nSigned-off-by: Alexa Griffith agriffith50@bloomberg.net\r\nSigned-off-by: alexagriffith \r\nSigned-off-by: Dan Sun \r\nCo-authored-by: Filippe Spolti \r\nCo-authored-by: Dan Sun ","shortMessageHtmlLink":"Update huggingface readme (#3678)"}},{"before":"ce9b0e8d631a665353de9a30d84ff2741601ea5c","after":"a4cce1a96fa0c7d3ecc916bd12505b529ed96337","ref":"refs/heads/master","pushedAt":"2024-05-11T10:15:57.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Update Dockerfile and Readme (#3676)\n\nSigned-off-by: Gavrish Prabhu ","shortMessageHtmlLink":"Update Dockerfile and Readme (#3676)"}},{"before":"ca50e18742c1761fd29298c3e370b71dfd677027","after":"ce9b0e8d631a665353de9a30d84ff2741601ea5c","ref":"refs/heads/master","pushedAt":"2024-05-10T02:01:22.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"fix for extract zip from gcs (#3510)\n\n* fix for extract zip from gcs\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* initial commit for gcs model download unittests\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* unittests for model download from gcs\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* black format fix\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n* code verification\r\n\r\nSigned-off-by: Andrews Arokiam \r\n\r\n---------\r\n\r\nSigned-off-by: Andrews Arokiam ","shortMessageHtmlLink":"fix for extract zip from gcs (#3510)"}},{"before":"a30d4029049802c262115ea4f80977a9c9b34405","after":"ca50e18742c1761fd29298c3e370b71dfd677027","ref":"refs/heads/master","pushedAt":"2024-05-10T01:58:36.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Add method for checking model health/readiness (#3673)\n\nSigned-off-by: Curtis Maddalozzo ","shortMessageHtmlLink":"Add method for checking model health/readiness (#3673)"}},{"before":"629e4aee83a5e4b7623de59bcdf1767eb3495d5d","after":"a30d4029049802c262115ea4f80977a9c9b34405","ref":"refs/heads/master","pushedAt":"2024-05-09T18:42:43.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Enable dtype support for huggingface server (#3613)\n\n* Enable dtype for huggingface server\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Set float16 as default. Fixup linter\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Add small comment to make the changes understandable\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Fixup linter\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Adapt to new huggingfacemodel\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Fixup merge :)\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Explicitly mention the behaviour of dtype flag on auto.\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Default to FP32 for encoder models\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Selectively add --dtype to parser. Use FP16 for GPU and FP32 for CPU\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Fixup linter\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Update poetry\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n* Use torch.float32 forr tests explicitly\r\n\r\nSigned-off-by: Dattu Sharma \r\n\r\n---------\r\n\r\nSigned-off-by: Dattu Sharma ","shortMessageHtmlLink":"Enable dtype support for huggingface server (#3613)"}},{"before":"d608056541e432c96cbb3f9291ebed8a61c90bd3","after":"629e4aee83a5e4b7623de59bcdf1767eb3495d5d","ref":"refs/heads/master","pushedAt":"2024-05-09T14:38:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"feat: Support customizable deployment strategy for RawDeployment mode. Fixes #3452 (#3603)\n\n* feat: Support customizable deployment strategy for RawDeployment mode\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* regen\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* lint\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Correctly apply rollingupdate\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* address comments\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n* Add validation\r\n\r\nSigned-off-by: Yuan Tang \r\n\r\n---------\r\n\r\nSigned-off-by: Yuan Tang ","shortMessageHtmlLink":"feat: Support customizable deployment strategy for RawDeployment mode. "}},{"before":"f3c3220f3979227af1870de59be2ad3e21404ea6","after":"d608056541e432c96cbb3f9291ebed8a61c90bd3","ref":"refs/heads/master","pushedAt":"2024-05-09T13:21:53.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"Add openai models endpoint (#3666)\n\nSigned-off-by: Curtis Maddalozzo ","shortMessageHtmlLink":"Add openai models endpoint (#3666)"}},{"before":"bfc2e21f50cbfd32c979afee2841ffe25000c7f4","after":"f3c3220f3979227af1870de59be2ad3e21404ea6","ref":"refs/heads/master","pushedAt":"2024-05-08T08:21:24.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"yuzisun","name":"Dan Sun","path":"/yuzisun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/7662095?s=80&v=4"},"commit":{"message":"upgrade vllm/transformers version (#3671)\n\nupgrade vllm version\r\n\r\nSigned-off-by: Johnu George ","shortMessageHtmlLink":"upgrade vllm/transformers version (#3671)"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEWwBhbQA","startCursor":null,"endCursor":null}},"title":"Activity · kserve/kserve"}