{"id":17747991,"url":"https://github.com/FMInference/FlexLLMGen","last_synced_at":"2025-03-14T23:32:00.405Z","repository":{"id":67653083,"uuid":"602270517","full_name":"FMInference/FlexLLMGen","owner":"FMInference","description":"Running large language models on a single GPU for throughput-oriented scenarios.","archived":true,"fork":false,"pushed_at":"2024-10-28T03:05:41.000Z","size":38932,"stargazers_count":9266,"open_issues_count":58,"forks_count":558,"subscribers_count":111,"default_branch":"main","last_synced_at":"2025-02-24T09:36:55.388Z","etag":null,"topics":["deep-learning","gpt-3","high-throughput","large-language-models","machine-learning","offloading","opt"],"latest_commit_sha":null,"homepage":"","language":"Python","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/FMInference.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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":"2023-02-15T21:18:53.000Z","updated_at":"2025-02-24T02:42:40.000Z","dependencies_parsed_at":"2024-04-19T20:37:40.908Z","dependency_job_id":"1fee7e94-da7a-48df-85ae-12e02a45f234","html_url":"https://github.com/FMInference/FlexLLMGen","commit_stats":{"total_commits":94,"total_committers":17,"mean_commits":5.529411764705882,"dds":0.4787234042553191,"last_synced_commit":"3834bb3eba206f5142ce555b44ad4979617eb989"},"previous_names":["fminference/flexigen","fminference/flexgen","fminference/flexllmgen","ying1123/flexgen"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FMInference%2FFlexLLMGen","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FMInference%2FFlexLLMGen/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FMInference%2FFlexLLMGen/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FMInference%2FFlexLLMGen/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FMInference","download_url":"https://codeload.github.com/FMInference/FlexLLMGen/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243663516,"owners_count":20327300,"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":["deep-learning","gpt-3","high-throughput","large-language-models","machine-learning","offloading","opt"],"created_at":"2024-10-26T10:01:03.591Z","updated_at":"2025-03-14T23:31:55.391Z","avatar_url":"https://github.com/FMInference.png","language":"Python","readme":null,"funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFMInference%2FFlexLLMGen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FFMInference%2FFlexLLMGen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFMInference%2FFlexLLMGen/lists"}