{"payload":{"header_redesign_enabled":false,"results":[{"id":"602270517","archived":false,"color":"#3572A5","followers":9038,"has_funding_file":false,"hl_name":"FMInference/FlexGen","hl_trunc_description":"Running large language models on a single GPU for throughput-oriented scenarios.","language":"Python","mirror":false,"owned_by_organization":true,"public":true,"repo":{"repository":{"id":602270517,"name":"FlexGen","owner_id":125944572,"owner_login":"FMInference","updated_at":"2024-04-19T19:33:37.171Z","has_issues":true}},"sponsorable":false,"topics":["machine-learning","deep-learning","offloading","high-throughput","opt","gpt-3","large-language-models"],"type":"Public","help_wanted_issues_count":3,"good_first_issue_issues_count":1,"starred_by_current_user":false}],"type":"repositories","page":1,"page_count":1,"elapsed_millis":71,"errors":[],"result_count":1,"facets":[],"protected_org_logins":[],"topics":null,"query_id":"","logged_in":false,"sign_up_path":"/signup?source=code_search_results","sign_in_path":"/login?return_to=https%3A%2F%2Fgithub.com%2Fsearch%3Fq%3Drepo%253AFMInference%252FFlexGen%2B%2Blanguage%253APython","metadata":null,"csrf_tokens":{"/FMInference/FlexGen/star":{"post":"TUsdLu1hP505lWtezv5QpO0jQPI73mo6bvc4pYPHC4kdplGFe4yVFo-QjcRsqztLBkuqVyc-tEi1eivLq0hMfw"},"/FMInference/FlexGen/unstar":{"post":"A5C8f1dMLGB3gDNyf8I5gay76m0Gc_F5aDzuLnk8Z3lXRfVUxXIuum_147lwMZt9ZI-kS5_oiiMvyUzuSca-mg"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"WM9MqD7sBE6pD4SbHYTouiW2GgbdfnLcVAe6F-tUVhd4aiJmiV_aabU5q7eNFiH-W5Wmqku_8DsaINrJVq1ntA"}}},"title":"Repository search results"}