{"data":{"slug":"raketenkater-ggrun","name":"ggrun","tagline":"Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp, OpenAI-compatible server with multi-GPU tensor-split, MoE expert placement, measured flag tuning (AI Tune), hardware-matched HuggingFac","github_url":"https://github.com/raketenkater/ggrun","owner":"raketenkater","repo":"ggrun","owner_avatar_url":"https://avatars.githubusercontent.com/u/49783786?v=4","primary_language":"Go","stars":254,"forks":14,"topics":["cuda","gguf","golang","inference-server","llama-cpp","llamacpp","llm","local-llm","localllama","metal","moe","multi-gpu","ollama-alternative","openai-api","self-hosted","speculative-decoding","vulkan"],"archived":false,"github_pushed_at":"2026-07-14T17:14:01+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/raketenkater-ggrun","markdown_url":"https://www.graphcanon.com/tools/raketenkater-ggrun.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/raketenkater-ggrun","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=raketenkater-ggrun","description":"Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp — OpenAI-compatible server with multi-GPU tensor-split, MoE expert placement, measured flag tuning (AI Tune), hardware-matched HuggingFace downloads, and crash recovery. An Ollama alternative for multi-GPU rigs.","homepage_url":null,"license":"MIT","open_issues":3,"watchers":4,"ai_summary":null,"readme_excerpt":null,"github_created_at":"2026-03-11T11:15:58+00:00","created_at":"2026-07-15T11:00:21.26198+00:00","updated_at":"2026-07-15T11:00:23.440104+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":"cuda","name":"cuda"},{"slug":"gguf","name":"gguf"},{"slug":"golang","name":"golang"},{"slug":"inference-server","name":"inference-server"},{"slug":"llama-cpp","name":"llama-cpp"},{"slug":"llamacpp","name":"llamacpp"},{"slug":"llm","name":"llm"},{"slug":"local-llm","name":"local-llm"}],"trust":{"provenance":{"is_fork":false,"github_id":1178786234,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-15T11:00:22.169Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":null,"days_since_push":0,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T11:00:22.527Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-15T11:00:21.933Z"},"languages":{"value":["go"],"source":"github.language","observed_at":"2026-07-15T11:00:21.933Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-15T11:00:21.933Z"}}}}