{"payload":{"header_redesign_enabled":false,"results":[{"id":"750973875","archived":false,"color":"#3572A5","followers":218,"has_funding_file":false,"hl_name":"SqueezeAILab/KVQuant","hl_trunc_description":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","language":"Python","mirror":false,"owned_by_organization":true,"public":true,"repo":{"repository":{"id":750973875,"name":"KVQuant","owner_id":92235103,"owner_login":"SqueezeAILab","updated_at":"2024-04-19T22:28:32.909Z","has_issues":true}},"sponsorable":false,"topics":["natural-language-processing","compression","text-generation","transformer","llama","quantization","mistral","model-compression","efficient-inference","efficient-model","large-language-models","llm","small-models","localllm","localllama"],"type":"Public","help_wanted_issues_count":0,"good_first_issue_issues_count":0,"starred_by_current_user":false}],"type":"repositories","page":1,"page_count":1,"elapsed_millis":81,"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%253ASqueezeAILab%252FKVQuant%2B%2Blanguage%253APython","metadata":null,"csrf_tokens":{"/SqueezeAILab/KVQuant/star":{"post":"_UoRWTDvI_GwR_aMXSOyycSBh6TQV291iJ_gVfGt-zq3hB5qCBAwdKP4OLjGzL1CIgbqJB00JxYktw5ngtGKew"},"/SqueezeAILab/KVQuant/unstar":{"post":"9KB91HWtyFT8qJkKas_P72Fm-BwQRv_DnDUrY1-120T0Q4YUZgmxj6ipA_UMqLqd6Col3fnElArGnrARFhQoZQ"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"Pw0_CtTbVmeotUCiqWwEQHtbHYpX0pjVKiaSDJWnPkI64d2m6MdQOHMbEfG4ZUJKEeT4XTAnmZjihum2pnI5EA"}}},"title":"Repository search results"}