{"payload":{"header_redesign_enabled":false,"results":[{"id":"765455287","archived":false,"color":"#3572A5","followers":152,"has_funding_file":false,"hl_name":"google/JetStream","hl_trunc_description":"JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs wel…","language":"Python","mirror":false,"owned_by_organization":true,"public":true,"repo":{"repository":{"id":765455287,"name":"JetStream","owner_id":1342004,"owner_login":"google","updated_at":"2024-06-07T22:59:54.518Z","has_issues":true}},"sponsorable":false,"topics":["gpu","inference","pytorch","transformer","llama","gpt","gemma","model-serving","tpu","jax","mlops","large-language-models","llm","llmops","llm-inference","llama2"],"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":70,"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%253Agoogle%252FJetStream%2B%2Blanguage%253APython","metadata":null,"csrf_tokens":{"/google/JetStream/star":{"post":"R-qdQ3lJwMk-Cxm0QPMQHnUGJULNT6AtQhac_slCn89unvQVLOBoX2f0QUl5xdc5AikI3rUG8nQb_k7c7EB-eA"},"/google/JetStream/unstar":{"post":"23x-4n3A84GLQX7o2W8PYUFMuSIIFPFPxFN9QD2F602AgoYyIWNvztu3sl2tod8hHs4-DwE-Hxu9B7138Wp7-Q"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"s9ho7VcFeakugoRlNgQK37rZL6yGQvW99tzX3pTOG7WC_7Ok_hGDYufH9wD54bHcHiRJfIJYSfO-LLRfeJmecQ"}}},"title":"Repository search results"}