{"id":679366051,"node_id":"R_kgDOKH5Now","name":"TensorRT-LLM","full_name":"NVIDIA/TensorRT-LLM","private":false,"owner":{"login":"NVIDIA","id":1728152,"node_id":"MDEyOk9yZ2FuaXphdGlvbjE3MjgxNTI=","avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","gravatar_id":"","url":"https://api.github.com/users/NVIDIA","html_url":"https://github.com/NVIDIA","followers_url":"https://api.github.com/users/NVIDIA/followers","following_url":"https://api.github.com/users/NVIDIA/following{/other_user}","gists_url":"https://api.github.com/users/NVIDIA/gists{/gist_id}","starred_url":"https://api.github.com/users/NVIDIA/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/NVIDIA/subscriptions","organizations_url":"https://api.github.com/users/NVIDIA/orgs","repos_url":"https://api.github.com/users/NVIDIA/repos","events_url":"https://api.github.com/users/NVIDIA/events{/privacy}","received_events_url":"https://api.github.com/users/NVIDIA/received_events","type":"Organization","user_view_type":"public","site_admin":false},"html_url":"https://github.com/NVIDIA/TensorRT-LLM","description":"TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.","fork":false,"url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM","forks_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/forks","keys_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/keys{/key_id}","collaborators_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/collaborators{/collaborator}","teams_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/teams","hooks_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/hooks","issue_events_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/issues/events{/number}","events_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/events","assignees_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/assignees{/user}","branches_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/branches{/branch}","tags_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/tags","blobs_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/git/blobs{/sha}","git_tags_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/git/tags{/sha}","git_refs_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/git/refs{/sha}","trees_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/git/trees{/sha}","statuses_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/statuses/{sha}","languages_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/languages","stargazers_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/stargazers","contributors_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/contributors","subscribers_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/subscribers","subscription_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/subscription","commits_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/commits{/sha}","git_commits_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/git/commits{/sha}","comments_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/comments{/number}","issue_comment_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/issues/comments{/number}","contents_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/contents/{+path}","compare_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/compare/{base}...{head}","merges_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/merges","archive_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/{archive_format}{/ref}","downloads_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/downloads","issues_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/issues{/number}","pulls_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/pulls{/number}","milestones_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/milestones{/number}","notifications_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/notifications{?since,all,participating}","labels_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/labels{/name}","releases_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/releases{/id}","deployments_url":"https://api.github.com/repos/NVIDIA/TensorRT-LLM/deployments","created_at":"2023-08-16T17:14:27Z","updated_at":"2026-04-20T03:08:14Z","pushed_at":"2026-04-20T03:08:08Z","git_url":"git://github.com/NVIDIA/TensorRT-LLM.git","ssh_url":"git@github.com:NVIDIA/TensorRT-LLM.git","clone_url":"https://github.com/NVIDIA/TensorRT-LLM.git","svn_url":"https://github.com/NVIDIA/TensorRT-LLM","homepage":"https://nvidia.github.io/TensorRT-LLM","size":1845148,"stargazers_count":13425,"watchers_count":13425,"language":"Python","has_issues":true,"has_projects":true,"has_downloads":true,"has_wiki":true,"has_pages":true,"has_discussions":true,"forks_count":2300,"mirror_url":null,"archived":false,"disabled":false,"open_issues_count":1336,"license":{"key":"other","name":"Other","spdx_id":"NOASSERTION","url":null,"node_id":"MDc6TGljZW5zZTA="},"allow_forking":true,"is_template":false,"web_commit_signoff_required":true,"has_pull_requests":true,"pull_request_creation_policy":"all","topics":["blackwell","cuda","llm-serving","moe","pytorch"],"visibility":"public","forks":2300,"open_issues":1336,"watchers":13425,"default_branch":"main","temp_clone_token":null,"custom_properties":{},"organization":{"login":"NVIDIA","id":1728152,"node_id":"MDEyOk9yZ2FuaXphdGlvbjE3MjgxNTI=","avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","gravatar_id":"","url":"https://api.github.com/users/NVIDIA","html_url":"https://github.com/NVIDIA","followers_url":"https://api.github.com/users/NVIDIA/followers","following_url":"https://api.github.com/users/NVIDIA/following{/other_user}","gists_url":"https://api.github.com/users/NVIDIA/gists{/gist_id}","starred_url":"https://api.github.com/users/NVIDIA/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/NVIDIA/subscriptions","organizations_url":"https://api.github.com/users/NVIDIA/orgs","repos_url":"https://api.github.com/users/NVIDIA/repos","events_url":"https://api.github.com/users/NVIDIA/events{/privacy}","received_events_url":"https://api.github.com/users/NVIDIA/received_events","type":"Organization","user_view_type":"public","site_admin":false},"network_count":2300,"subscribers_count":126}