{"id":13458593,"url":"https://nvidia.github.io/TensorRT-LLM/","last_synced_at":"2025-03-24T15:31:42.022Z","repository":{"id":201227926,"uuid":"679366051","full_name":"NVIDIA/TensorRT-LLM","owner":"NVIDIA","description":"TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.","archived":false,"fork":false,"pushed_at":"2025-03-21T07:43:37.000Z","size":951977,"stargazers_count":9759,"open_issues_count":540,"forks_count":1177,"subscribers_count":115,"default_branch":"main","last_synced_at":"2025-03-21T18:01:55.752Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://nvidia.github.io/TensorRT-LLM","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NVIDIA.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-16T17:14:27.000Z","updated_at":"2025-03-21T08:44:52.000Z","dependencies_parsed_at":"2025-03-21T07:37:19.544Z","dependency_job_id":null,"html_url":"https://github.com/NVIDIA/TensorRT-LLM","commit_stats":{"total_commits":120,"total_committers":19,"mean_commits":6.315789473684211,"dds":0.3416666666666667,"last_synced_commit":"be1788106245496872d18e702978e59b6bfd50e0"},"previous_names":["nvidia/tensorrt-llm"],"tags_count":17,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FTensorRT-LLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FTensorRT-LLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FTensorRT-LLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2FTensorRT-LLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA","download_url":"https://codeload.github.com/NVIDIA/TensorRT-LLM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245298097,"owners_count":20592541,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T09:00:54.276Z","updated_at":"2025-03-24T15:31:37.014Z","avatar_url":"https://github.com/NVIDIA.png","language":"C++","funding_links":[],"categories":["Projects","🛠️ Tutorials \u0026 Cookbooks","Model Serving","📖Contents"],"sub_categories":["Inference","T18 · Inference \u0026 Serving","📖LLM Train/Inference Framework/Design ([©️back👆🏻](#paperlist))"],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/nvidia.github.io%2FTensorRT-LLM%2F","html_url":"https://awesome.ecosyste.ms/projects/nvidia.github.io%2FTensorRT-LLM%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/nvidia.github.io%2FTensorRT-LLM%2F/lists"}