{"id":27232933,"url":"https://github.com/NLPOptimize/flash-tokenizer","last_synced_at":"2025-04-10T14:11:17.224Z","repository":{"id":281422211,"uuid":"945231616","full_name":"NLPOptimize/flash-tokenizer","owner":"NLPOptimize","description":"EFFICIENT AND OPTIMIZED TOKENIZER ENGINE FOR LLM INFERENCE SERVING","archived":false,"fork":false,"pushed_at":"2025-04-09T09:26:39.000Z","size":204490,"stargazers_count":287,"open_issues_count":1,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-09T10:39:14.707Z","etag":null,"topics":["bert","berttokenizer","cpp","cpp17","deep-learning","flash","huggingface","nlp","pybind11","python","tokenizer","trie","wordpiece","wordpiece-tokenization"],"latest_commit_sha":null,"homepage":"https://github.com/NLPOptimize/flash-tokenizer","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NLPOptimize.png","metadata":{"files":{"readme":"README.ja-JP.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-03-09T00:26:27.000Z","updated_at":"2025-04-09T10:22:48.000Z","dependencies_parsed_at":"2025-03-29T05:22:03.707Z","dependency_job_id":null,"html_url":"https://github.com/NLPOptimize/flash-tokenizer","commit_stats":null,"previous_names":["nlpoptimize/flash-tokenizer"],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NLPOptimize%2Fflash-tokenizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NLPOptimize%2Fflash-tokenizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NLPOptimize%2Fflash-tokenizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NLPOptimize%2Fflash-tokenizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NLPOptimize","download_url":"https://codeload.github.com/NLPOptimize/flash-tokenizer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248025867,"owners_count":21035556,"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":["bert","berttokenizer","cpp","cpp17","deep-learning","flash","huggingface","nlp","pybind11","python","tokenizer","trie","wordpiece","wordpiece-tokenization"],"created_at":"2025-04-10T14:11:09.990Z","updated_at":"2025-04-10T14:11:12.212Z","avatar_url":"https://github.com/NLPOptimize.png","language":"C++","readme":null,"funding_links":[],"categories":["🔹 **WordPiece Tokenizer Implementations**","Tools 🛠️"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNLPOptimize%2Fflash-tokenizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FNLPOptimize%2Fflash-tokenizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNLPOptimize%2Fflash-tokenizer/lists"}