{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":766511988,"defaultBranch":"main","name":"vllm","ownerLogin":"leixy76","currentUserCanPush":false,"isFork":true,"isEmpty":false,"createdAt":"2024-03-03T13:27:05.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/162015206?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1709472437.457429","currentOid":""},"activityList":{"items":[{"before":"774d1035e4000fe3a40e01ccbf017a0f763fd6f2","after":"4a6769053ab2616f7f490e6ec5b8241e76ef0c2a","ref":"refs/heads/main","pushedAt":"2024-06-16T14:36:59.000Z","pushType":"push","commitsCount":84,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[CI][BugFix] Flip is_quant_method_supported condition (#5577)","shortMessageHtmlLink":"[CI][BugFix] Flip is_quant_method_supported condition (vllm-project#5577"}},{"before":"7b0a0dfb22907505441f8a4a5eb882cbca4d2acf","after":"774d1035e4000fe3a40e01ccbf017a0f763fd6f2","ref":"refs/heads/main","pushedAt":"2024-06-10T14:54:48.000Z","pushType":"push","commitsCount":32,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Feature][Frontend]: Continued `stream_options` implementation also in CompletionRequest (#5319)","shortMessageHtmlLink":"[Feature][Frontend]: Continued stream_options implementation also i…"}},{"before":"06b2550cbb56f4a538f43c56addf20f4d2d19cad","after":"7b0a0dfb22907505441f8a4a5eb882cbca4d2acf","ref":"refs/heads/main","pushedAt":"2024-06-06T09:26:14.000Z","pushType":"push","commitsCount":31,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Frontend][Core] Update Outlines Integration from `FSM` to `Guide` (#4109)\n\nCo-authored-by: Simon Mo \r\nCo-authored-by: Breno Faria ","shortMessageHtmlLink":"[Frontend][Core] Update Outlines Integration from FSM to Guide (v…"}},{"before":"f790ad3c50f050778af1fd31170746b7c68ca2fc","after":"06b2550cbb56f4a538f43c56addf20f4d2d19cad","ref":"refs/heads/main","pushedAt":"2024-06-04T01:52:01.000Z","pushType":"push","commitsCount":10,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Bugfix] Support `prompt_logprobs==0` (#5217)","shortMessageHtmlLink":"[Bugfix] Support prompt_logprobs==0 (vllm-project#5217)"}},{"before":"d4f398590786f0015d474b03a3d078db1e7d1be2","after":"f790ad3c50f050778af1fd31170746b7c68ca2fc","ref":"refs/heads/main","pushedAt":"2024-06-02T14:56:36.000Z","pushType":"push","commitsCount":46,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Frontend][OpenAI] Support for returning max_model_len on /v1/models response (#4643)","shortMessageHtmlLink":"[Frontend][OpenAI] Support for returning max_model_len on /v1/models …"}},{"before":"f17a1a8f9665bb237a3dddda7dc93f259e5e81e0","after":"d4f398590786f0015d474b03a3d078db1e7d1be2","ref":"refs/heads/main","pushedAt":"2024-05-28T09:57:01.000Z","pushType":"push","commitsCount":4,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Core] Sliding window for block manager v2 (#4545)\n\nCo-authored-by: Ruth Evans ","shortMessageHtmlLink":"[Core] Sliding window for block manager v2 (vllm-project#4545)"}},{"before":"86b45ae065e8c5e4a5f2af3ee1dc19a261c58775","after":"f17a1a8f9665bb237a3dddda7dc93f259e5e81e0","ref":"refs/heads/main","pushedAt":"2024-05-26T08:50:29.000Z","pushType":"push","commitsCount":40,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Misc] Make Serving Benchmark More User-friendly (#5044)","shortMessageHtmlLink":"[Misc] Make Serving Benchmark More User-friendly (vllm-project#5044)"}},{"before":"26148120b3c05704409a425d017f0a51fca3b7cc","after":"86b45ae065e8c5e4a5f2af3ee1dc19a261c58775","ref":"refs/heads/main","pushedAt":"2024-05-17T23:56:46.000Z","pushType":"push","commitsCount":4,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Bugfix] Relax tiktoken to >= 0.6.0 (#4890)","shortMessageHtmlLink":"[Bugfix] Relax tiktoken to >= 0.6.0 (vllm-project#4890)"}},{"before":"a5675d348b126e53928e139d1ed5b2c00a0044e8","after":"26148120b3c05704409a425d017f0a51fca3b7cc","ref":"refs/heads/main","pushedAt":"2024-05-17T09:15:25.000Z","pushType":"push","commitsCount":21,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Build/CI] Extending the set of AMD tests with Regression, Basic Correctness, Distributed, Engine, Llava Tests (#4797)","shortMessageHtmlLink":"[Build/CI] Extending the set of AMD tests with Regression, Basic Corr…"}},{"before":"ccb63a8245bceb9e6ba260eeef41b54ca8bdb370","after":"a5675d348b126e53928e139d1ed5b2c00a0044e8","ref":"refs/heads/main","pushedAt":"2024-05-15T14:55:42.000Z","pushType":"push","commitsCount":7,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Bugfix] Properly set distributed_executor_backend in ParallelConfig (#4816)","shortMessageHtmlLink":"[Bugfix] Properly set distributed_executor_backend in ParallelConfig (v…"}},{"before":"4bfa7e7f75eb5b1a397c93aeea1dea1afa867b2a","after":"ccb63a8245bceb9e6ba260eeef41b54ca8bdb370","ref":"refs/heads/main","pushedAt":"2024-05-14T14:41:05.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Core][Hash][Automatic Prefix caching] Accelerating the hashing function by avoiding deep copies (#4696)","shortMessageHtmlLink":"[Core][Hash][Automatic Prefix caching] Accelerating the hashing funct…"}},{"before":"c83310174055bb124ea2197885b652efd59b7a0f","after":"4bfa7e7f75eb5b1a397c93aeea1dea1afa867b2a","ref":"refs/heads/main","pushedAt":"2024-05-14T01:15:34.000Z","pushType":"push","commitsCount":24,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Doc] Add API reference for offline inference (#4710)","shortMessageHtmlLink":"[Doc] Add API reference for offline inference (vllm-project#4710)"}},{"before":"63575bc2e197b85ce1c911421ff30c5459e35e9c","after":"c83310174055bb124ea2197885b652efd59b7a0f","ref":"refs/heads/main","pushedAt":"2024-05-10T01:03:33.000Z","pushType":"push","commitsCount":27,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Kernel] Refactor FP8 kv-cache with NVIDIA float8_e4m3 support (#4535)","shortMessageHtmlLink":"[Kernel] Refactor FP8 kv-cache with NVIDIA float8_e4m3 support (vllm-…"}},{"before":"a395a638c2f18d549e7d01655cf7a6dbee566f91","after":"63575bc2e197b85ce1c911421ff30c5459e35e9c","ref":"refs/heads/main","pushedAt":"2024-05-07T05:47:17.000Z","pushType":"push","commitsCount":105,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Core][Optimization] change python dict to pytorch tensor (#4607)","shortMessageHtmlLink":"[Core][Optimization] change python dict to pytorch tensor (vllm-proje…"}},{"before":"077f0a2e8a873340b1a2cf54d6c9043754eb7514","after":"a395a638c2f18d549e7d01655cf7a6dbee566f91","ref":"refs/heads/main","pushedAt":"2024-04-25T01:40:38.000Z","pushType":"push","commitsCount":26,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Misc] Use public API in benchmark_throughput (#4300)","shortMessageHtmlLink":"[Misc] Use public API in benchmark_throughput (vllm-project#4300)"}},{"before":"8438e0569eaf8496aa3d41deb808f2c831b64ecf","after":"077f0a2e8a873340b1a2cf54d6c9043754eb7514","ref":"refs/heads/main","pushedAt":"2024-04-22T09:41:48.000Z","pushType":"push","commitsCount":33,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Frontend] Enable support for CPU backend in AsyncLLMEngine. (#3993)\n\nSigned-off-by: Tao He ","shortMessageHtmlLink":"[Frontend] Enable support for CPU backend in AsyncLLMEngine. (vllm-pr…"}},{"before":"5c2e66e4871917c5d59cc4a8b89ef53e690e9bd9","after":"8438e0569eaf8496aa3d41deb808f2c831b64ecf","ref":"refs/heads/main","pushedAt":"2024-04-17T09:09:30.000Z","pushType":"push","commitsCount":22,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Core] RayWorkerVllm --> WorkerWrapper to reduce duplication (#4024)\n\n[Core] replace narrow-usage RayWorkerVllm to general WorkerWrapper to reduce code duplication (#4024)","shortMessageHtmlLink":"[Core] RayWorkerVllm --> WorkerWrapper to reduce duplication (vllm-pr…"}},{"before":"546e7211684a28bbe53088961b4cf5123e235760","after":"5c2e66e4871917c5d59cc4a8b89ef53e690e9bd9","ref":"refs/heads/main","pushedAt":"2024-04-13T08:19:52.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Bugfix] More type hint fixes for py 3.8 (#4039)","shortMessageHtmlLink":"[Bugfix] More type hint fixes for py 3.8 (vllm-project#4039)"}},{"before":"f3d0bf7589d6e63a691dcbb9d1db538c184fde29","after":"546e7211684a28bbe53088961b4cf5123e235760","ref":"refs/heads/main","pushedAt":"2024-04-13T04:03:42.000Z","pushType":"push","commitsCount":19,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[CI/Test] expand ruff and yapf for all supported python version (#4037)","shortMessageHtmlLink":"[CI/Test] expand ruff and yapf for all supported python version (vllm…"}},{"before":"2f1928354903ae0c6edfe76cc90081eb513ead2c","after":"f3d0bf7589d6e63a691dcbb9d1db538c184fde29","ref":"refs/heads/main","pushedAt":"2024-04-11T03:44:20.000Z","pushType":"push","commitsCount":27,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Doc][Installation] delete python setup.py develop (#3989)","shortMessageHtmlLink":"[Doc][Installation] delete python setup.py develop (vllm-project#3989)"}},{"before":"54951ac4bfb7f4224cb8f5ffc89b214c950107d8","after":"2f1928354903ae0c6edfe76cc90081eb513ead2c","ref":"refs/heads/main","pushedAt":"2024-04-07T14:35:47.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Core] latency optimization (#3890)","shortMessageHtmlLink":"[Core] latency optimization (vllm-project#3890)"}},{"before":"cfaf49a1673c872d2a06560346efb13695f82f35","after":"54951ac4bfb7f4224cb8f5ffc89b214c950107d8","ref":"refs/heads/main","pushedAt":"2024-04-06T14:59:55.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Bugfix] Fix incorrect output on OLMo models in Tensor Parallelism (#3869)","shortMessageHtmlLink":"[Bugfix] Fix incorrect output on OLMo models in Tensor Parallelism (v…"}},{"before":"c64cf38673780544087af5ad5d3baf879a29220b","after":"cfaf49a1673c872d2a06560346efb13695f82f35","ref":"refs/heads/main","pushedAt":"2024-04-05T14:16:03.000Z","pushType":"push","commitsCount":19,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Misc] Define common requirements (#3841)","shortMessageHtmlLink":"[Misc] Define common requirements (vllm-project#3841)"}},{"before":"0739b1947f4081b0edafc7951134a928e39302e7","after":"c64cf38673780544087af5ad5d3baf879a29220b","ref":"refs/heads/main","pushedAt":"2024-04-03T14:33:49.000Z","pushType":"push","commitsCount":9,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Doc] Update contribution guidelines for better onboarding (#3819)","shortMessageHtmlLink":"[Doc] Update contribution guidelines for better onboarding (vllm-proj…"}},{"before":"f03cc667a09bce92e09365893603f7ec0d87c9f2","after":"0739b1947f4081b0edafc7951134a928e39302e7","ref":"refs/heads/main","pushedAt":"2024-04-02T14:18:19.000Z","pushType":"push","commitsCount":8,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Frontend][Bugfix] allow using the default middleware with a root path (#3788)\n\nCo-authored-by: A-Mahla <>","shortMessageHtmlLink":"[Frontend][Bugfix] allow using the default middleware with a root path ("}},{"before":"563c1d7ec56aa0f9fdc28720f3517bf9297f5476","after":"f03cc667a09bce92e09365893603f7ec0d87c9f2","ref":"refs/heads/main","pushedAt":"2024-04-01T15:06:52.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Misc] Minor fixes in requirements.txt (#3769)","shortMessageHtmlLink":"[Misc] Minor fixes in requirements.txt (vllm-project#3769)"}},{"before":"51c31bc10ca7c48b580cd58fcd741ba4d6db4447","after":"563c1d7ec56aa0f9fdc28720f3517bf9297f5476","ref":"refs/heads/main","pushedAt":"2024-03-31T14:13:14.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[CI/Build] Make Marlin Tests Green (#3753)","shortMessageHtmlLink":"[CI/Build] Make Marlin Tests Green (vllm-project#3753)"}},{"before":"3c5ab9b811da7a72af6459bc0c344644ebdc1ef6","after":"51c31bc10ca7c48b580cd58fcd741ba4d6db4447","ref":"refs/heads/main","pushedAt":"2024-03-30T09:51:54.000Z","pushType":"push","commitsCount":67,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"CMake build elf without PTX (#3739)","shortMessageHtmlLink":"CMake build elf without PTX (vllm-project#3739)"}},{"before":"f721096d48a7e3b98dffcb9b400bf58989cef64d","after":"3c5ab9b811da7a72af6459bc0c344644ebdc1ef6","ref":"refs/heads/main","pushedAt":"2024-03-24T09:24:13.000Z","pushType":"push","commitsCount":4,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[Misc] Fix BLOOM copyright notice (#3591)","shortMessageHtmlLink":"[Misc] Fix BLOOM copyright notice (vllm-project#3591)"}},{"before":"4c07dd28c0ef8642735222e077935b55f4c98017","after":"f721096d48a7e3b98dffcb9b400bf58989cef64d","ref":"refs/heads/main","pushedAt":"2024-03-22T13:31:18.000Z","pushType":"push","commitsCount":6,"pusher":{"login":"leixy76","name":null,"path":"/leixy76","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/162015206?s=80&v=4"},"commit":{"message":"[BugFix] Some fixes for custom allreduce kernels (#2760)","shortMessageHtmlLink":"[BugFix] Some fixes for custom allreduce kernels (vllm-project#2760)"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEZqziGwA","startCursor":null,"endCursor":null}},"title":"Activity · leixy76/vllm"}