{"data":{"slug":"jmaczan-tiny-vllm","name":"tiny-vllm","tagline":"Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM","github_url":"https://github.com/jmaczan/tiny-vllm","owner":"jmaczan","repo":"tiny-vllm","owner_avatar_url":"https://avatars.githubusercontent.com/u/18054202?v=4","primary_language":"C++","stars":909,"forks":61,"topics":["ai","attention","batching","course","cpp","cuda","hpc","inference","llm","llm-inference","pagedattention","tiny-vllm","vllm"],"archived":false,"github_pushed_at":"2026-07-02T18:32:16+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/jmaczan-tiny-vllm","markdown_url":"https://www.graphcanon.com/tools/jmaczan-tiny-vllm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jmaczan-tiny-vllm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jmaczan-tiny-vllm","description":"Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM","homepage_url":null,"license":"Apache-2.0","open_issues":1,"watchers":3,"ai_summary":null,"readme_excerpt":null,"github_created_at":"2026-02-09T16:40:15+00:00","created_at":"2026-07-11T11:44:10.840335+00:00","updated_at":"2026-07-11T11:44:12.939723+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"attention","name":"attention"},{"slug":"batching","name":"batching"},{"slug":"course","name":"course"},{"slug":"cpp","name":"cpp"},{"slug":"cuda","name":"cuda"},{"slug":"hpc","name":"hpc"},{"slug":"inference","name":"inference"}],"trust":{"provenance":{"is_fork":false,"github_id":1153764295,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T11:44:11.422Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":null,"days_since_push":8,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:44:11.972Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T11:44:11.741Z"},"languages":{"value":["c++"],"source":"github.language","observed_at":"2026-07-11T11:44:11.741Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-11T11:44:11.741Z"}}}}