{"id":48954198,"url":"https://github.com/iamwavecut/llama-cpp-triattention","last_synced_at":"2026-04-17T22:33:17.367Z","repository":{"id":350324239,"uuid":"1206322353","full_name":"iamwavecut/llama-cpp-triattention","owner":"iamwavecut","description":"llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.","archived":false,"fork":false,"pushed_at":"2026-04-09T20:26:30.000Z","size":304303,"stargazers_count":0,"open_issues_count":6,"forks_count":0,"subscribers_count":0,"default_branch":"triattention","last_synced_at":"2026-04-09T22:17:23.458Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iamwavecut.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":"AUTHORS","dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-09T19:55:24.000Z","updated_at":"2026-04-09T20:26:37.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/iamwavecut/llama-cpp-triattention","commit_stats":null,"previous_names":["iamwavecut/llama-cpp-triattention"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/iamwavecut/llama-cpp-triattention","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iamwavecut%2Fllama-cpp-triattention","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iamwavecut%2Fllama-cpp-triattention/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iamwavecut%2Fllama-cpp-triattention/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iamwavecut%2Fllama-cpp-triattention/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iamwavecut","download_url":"https://codeload.github.com/iamwavecut/llama-cpp-triattention/tar.gz/refs/heads/triattention","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iamwavecut%2Fllama-cpp-triattention/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31948523,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-17T17:29:20.459Z","status":"ssl_error","status_checked_at":"2026-04-17T17:28:47.801Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2026-04-17T22:33:11.620Z","updated_at":"2026-04-17T22:33:12.351Z","avatar_url":"https://github.com/iamwavecut.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiamwavecut%2Fllama-cpp-triattention","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiamwavecut%2Fllama-cpp-triattention","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiamwavecut%2Fllama-cpp-triattention/lists"}