{"payload":{"header_redesign_enabled":false,"results":[{"id":"670332256","archived":false,"color":"#f34b7d","followers":305,"has_funding_file":false,"hl_name":"vectorch-ai/ScaleLLM","hl_trunc_description":"A high-performance inference system for large language models, designed for production environments.","language":"C++","mirror":false,"owned_by_organization":true,"public":true,"repo":{"repository":{"id":670332256,"name":"ScaleLLM","owner_id":136120791,"owner_login":"vectorch-ai","updated_at":"2024-06-04T11:08:51.234Z","has_issues":true}},"sponsorable":false,"topics":["performance","gpu","model","production","cuda","efficiency","inference","transformer","llama","speculative","serving","llm","llm-inference","llama3"],"type":"Public","help_wanted_issues_count":0,"good_first_issue_issues_count":1,"starred_by_current_user":false}],"type":"repositories","page":1,"page_count":1,"elapsed_millis":85,"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%253Avectorch-ai%252FScaleLLM%2B%2Blanguage%253AC%252B%252B","metadata":null,"csrf_tokens":{"/vectorch-ai/ScaleLLM/star":{"post":"DkjOebuv0kskuVXLsUm8kmzIix87UcienvWUyXD-j7VJzvwzGKMPhKh3k1lC21yUh18UpRj7Olg7jr4iZuETYA"},"/vectorch-ai/ScaleLLM/unstar":{"post":"TnLWb8e11T3WXN-9KN2dwxBuml75DCxn7Ze4IwfmT76Yd8RGa8qvBhZqeCaHH84fSJeES9DQx_HlR0_GRJ1NrA"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"M7FifVXQrvRXB6j0h--KpqXo5NZEqMsHQZh0r2s2pwk1cNLjvxgIBzkH-ySukY5Sz1FO48gz9w64EV7sgLFQeg"}}},"title":"Repository search results"}